© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2915
    Prev
    Next
    INDEX
    Explanations

    apostrophes and other characters typically found in contractions

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    '
    -0.71
    LL
    -0.69
    ll
    -0.66
    ’
    -0.65
     LL
    -0.56
     ll
    -0.54
    <bos>
    -0.52
     d
    -0.46
    lihood
    -0.39
    3
    -0.38
    POSITIVE LOGITS
    criminator
    0.69
    intios
    0.69
     Walkover
    0.68
    inhua
    0.66
     Chwiliwch
    0.65
    matan
    0.65
    arques
    0.65
     kasarigan
    0.63
    arkov
    0.63
    ksesta
    0.63
    Activations Density 12.630%

    No Known Activations