© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12987
    Prev
    Next
    INDEX
    Explanations

    academic writing, especially citations, references to other arguments, and discussion and rebuttals of other points of view.

    oai_token-act-pair · gemini-2.0-flash

    words related to compatibility and choices

    np_token-act-pair-logits · gpt-4o-mini

    academic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.62
    RetentionPolicy
    -0.62
    VolleyError
    -0.61
     surla
    -0.60
     resourceCulture
    -0.58
    ValueGeneration
    -0.58
     découver
    -0.57
     كومونز
    -0.57
    astify
    -0.57
    NOPQRST
    -0.56
    POSITIVE LOGITS
     compatible
    0.56
     link
    0.55
     internal
    0.53
     inextrica
    0.52
     incomplete
    0.52
    atible
    0.51
     Compatible
    0.50
    essoal
    0.49
     char
    0.49
     inseparable
    0.49
    Activations Density 2.603%

    No Known Activations