© 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. 4102
    Prev
    Next
    INDEX
    Explanations

    a jumbled collection of words with no clear underlying thread.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and coding syntax

    np_token-act-pair-logits · gpt-4o-mini
    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
    there
    -0.60
     Temos
    -0.51
    There
    -0.49
    "}")
    -0.48
    THERE
    -0.46
    astify
    -0.46
     XNUMX
    -0.45
     }}$.
    -0.45
    ExtendWith
    -0.45
    Скачать
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.77
     Савезне
    0.73
     @"/
    0.73
    SourceChecksum
    0.70
     the
    0.68
    tagHelperRunner
    0.66
    ایج
    0.66
     jScrollPane
    0.65
    featureID
    0.63
    횟
    0.62
    Activations Density 2.884%

    No Known Activations