© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14887
    Prev
    Next
    INDEX
    Explanations

    phrases of possibility or conditionality

    oai_token-act-pair · gemini-2.0-flash

    words indicating necessity or appropriateness

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

    Evaluations and judgements

    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
     ujednoznacz
    -0.72
     DataTypes
    -0.58
    RenderAtEndOf
    -0.56
     ProtoMessage
    -0.54
    LookAnd
    -0.54
    bildēt
    -0.53
     voors
    -0.53
     mergeFrom
    -0.53
     ISNI
    -0.52
    mybatisplus
    -0.52
    POSITIVE LOGITS
    ]--;
    0.63
     fitting
    0.59
     appropriate
    0.54
     fitter
    0.54
    appropriate
    0.52
    fitting
    0.52
    σιμο
    0.51
     AssemblyCulture
    0.50
     Fitting
    0.49
     necessary
    0.48
    Activations Density 1.051%

    No Known Activations