© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9499
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially last names, followed by "said" or similar verbs of communication

    oai_token-act-pair · gemini-2.0-flash

    Quotations and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     sumpay
    -0.48
     ModelExpression
    -0.47
    iconque
    -0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.45
    orgon
    -0.43
    cassert
    -0.42
    cstring
    -0.41
     Frö
    -0.41
     Em
    -0.41
    iostream
    -0.41
    POSITIVE LOGITS
     disambiguazione
    0.63
    ⓧ
    0.60
    StoreMessageInfo
    0.59
    AccessorTable
    0.59
     незавершена
    0.59
    RTLI
    0.57
    HasAnnotation
    0.57
    ьаж
    0.56
    ServletException
    0.56
    Xna
    0.56
    Activations Density 0.176%

    No Known Activations