© 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. 2346
    Prev
    Next
    INDEX
    Explanations

    words fragments that don't mean much of anything by themselves.

    oai_token-act-pair · gemini-2.0-flash

    words related to calculation and process

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

    illa

    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
     kasarigan
    -0.91
     nakalista
    -0.79
    writeFieldEnd
    -0.75
     ExecuteAsync
    -0.75
     ProtoMessage
    -0.72
    Carcinogenicity
    -0.70
    toMatchSnapshot
    -0.69
    RenderAtEndOf
    -0.68
    contentLoaded
    -0.67
    ruptedException
    -0.66
    POSITIVE LOGITS
    use
    0.47
    ukseen
    0.46
    Hab
    0.45
    ima
    0.45
     goûts
    0.45
    Hack
    0.45
    Aktualisiert
    0.42
    ir
    0.42
     poda
    0.42
     morire
    0.42
    Activations Density 1.252%

    No Known Activations