© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2426
    Prev
    Next
    INDEX
    Explanations

    parenthetical asides and citations

    oai_token-act-pair · gemini-2.0-flash

    journal citations

    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
     purpoſe
    -0.65
     Theſe
    -0.60
     tranſ
    -0.59
     myſelf
    -0.55
     raiſ
    -0.54
    Билгалдахарш
    -0.54
     deſt
    -0.54
     Beſ
    -0.53
     Hift
    -0.53
     Reſ
    -0.52
    POSITIVE LOGITS
    stanza
    0.59
     thức
    0.52
    forestation
    0.50
     Lead
    0.48
    ☆☆☆☆
    0.47
    dbury
    0.47
     Grunde
    0.47
    wahati
    0.46
    msgid
    0.45
    ishman
    0.44
    Activations Density 0.612%

    No Known Activations