© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12963
    Prev
    Next
    INDEX
    Explanations

    the prefix "cy" and "ky" (all case-insensitive)

    oai_token-act-pair · gemini-2.0-flash

    cy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    edish
    -0.50
     conf
    -0.45
     colt
    -0.43
     im
    -0.43
    moveToFirst
    -0.43
    Referințe
    -0.42
     dateFormat
    -0.40
    lequin
    -0.40
    êche
    -0.40
    дз
    -0.40
    POSITIVE LOGITS
    LookAnd
    0.81
    NewUrlParser
    0.75
    OGND
    0.72
    findpost
    0.71
    новниш
    0.65
    extAlignment
    0.64
     Wikimedijinoj
    0.64
    transQ
    0.63
     Audiodateien
    0.62
    UserScript
    0.60
    Activations Density 1.411%

    No Known Activations