© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12313
    Prev
    Next
    INDEX
    Explanations

    the word "hole"

    oai_token-act-pair · gemini-2.0-flash

    hole

    np_max-act · gemini-2.0-flash

    ▁hole Method used: 1 — identical max tokens, ▁hole

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    balleur
    -0.69
     Bioaccumulative
    -0.63
    quatch
    -0.63
    )_/¯
    -0.62
     INTERESAR
    -0.62
     mapStateToProps
    -0.62
    igurumi
    -0.61
     StatefulWidget
    -0.60
    <?>>
    -0.60
     “
    -0.60
    POSITIVE LOGITS
     ―――――
    0.72
    OGND
    0.72
     Reſ
    0.66
    bootstrapcdn
    0.65
     חיצוניים
    0.64
    ParallelGroup
    0.63
     Houſe
    0.62
     Perſ
    0.59
    MLLoader
    0.59
     orientação
    0.59
    Activations Density 1.265%

    No Known Activations