© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11610
    Prev
    Next
    INDEX
    Explanations

    mixed foreign words

    oai_token-act-pair · gemini-2.0-flash

    word patterns resembling code or programming syntax

    np_token-act-pair-logits · gpt-4o-mini

    Code and experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ніципалі
    -0.72
     Meksiku
    -0.55
    guero
    -0.53
     '\\;'
    -0.52
    Istorija
    -0.52
    LCA
    -0.52
     @"/
    -0.51
     mergeFrom
    -0.50
    leine
    -0.50
    usa
    -0.50
    POSITIVE LOGITS
    enumi
    0.69
    migrationBuilder
    0.63
    __*/
    0.53
     rumahnya
    0.48
     Италијани
    0.47
    ngths
    0.46
    getSupport
    0.46
    éndole
    0.46
     morire
    0.46
    subpackage
    0.45
    Activations Density 0.154%

    No Known Activations