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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12066
    Prev
    Next
    INDEX
    Explanations

    phrases describing an action or event that is taking place

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'tra'

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

    racing

    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
     typelib
    -0.77
    ()?;
    -0.72
     ſy
    -0.72
    ElementException
    -0.71
     Cæsar
    -0.69
     Confucian
    -0.69
    VolleyError
    -0.68
    OrBuilder
    -0.68
     Pythag
    -0.67
     Neander
    -0.65
    POSITIVE LOGITS
     la
    0.49
    TRIBUN
    0.43
    :][
    0.42
    マーク
    0.41
    inp
    0.40
     labor
    0.40
     traveling
    0.40
    cot
    0.38
    ipat
    0.38
    rop
    0.38
    Activations Density 1.236%

    No Known Activations