© 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. 11070
    Prev
    Next
    INDEX
    Explanations

    text discussing numerical facts about sizes, from percentages to area ranks

    oai_token-act-pair · gemini-2.0-flash

    relative size or importance

    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
    a
    -0.68
     HttpNotFound
    -0.63
    aryen
    -0.63
     a
    -0.59
    e
    -0.57
    IntoConstraints
    -0.56
    z
    -0.56
    ap
    -0.52
     صوتيه
    -0.51
    r
    -0.51
    POSITIVE LOGITS
     of
    0.82
    ItemLayout
    0.69
     ofthe
    0.67
     ofre
    0.61
    invokeLater
    0.59
    PreferredItem
    0.57
    Fordítás
    0.54
    fiez
    0.54
    ⪢
    0.53
     vectorielles
    0.52
    Activations Density 13.559%

    No Known Activations