© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1439
    Prev
    Next
    INDEX
    Explanations

    sentences containing words like "may", "must", "would," and "could" that express conditions or possibility

    oai_token-act-pair · gemini-2.0-flash

    Hypothetical situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ro
    -0.54
    de
    -0.51
    ll
    -0.48
    him
    -0.46
     come
    -0.44
    ero
    -0.44
     controlled
    -0.43
    st
    -0.43
    sp
    -0.43
    RO
    -0.42
    POSITIVE LOGITS
    findpost
    0.96
    الحياه
    0.90
    KommentareTeilen
    0.90
     ModelExpression
    0.88
     Normdatei
    0.86
    Hochspringen
    0.85
     FetchType
    0.83
    enumii
    0.82
    RenderAtEndOf
    0.80
    principalTable
    0.80
    Activations Density 1.326%

    No Known Activations