© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15382
    Prev
    Next
    INDEX
    Explanations

    XML code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     mío
    -0.42
     lainnya
    -0.42
    BeginInit
    -0.41
     prénom
    -0.41
    łaś
    -0.40
    Quote
    -0.40
    bindParam
    -0.39
     mía
    -0.35
     teil
    -0.35
    Stiftung
    -0.35
    POSITIVE LOGITS
     disambiguazione
    0.90
    __(/*!
    0.89
     Roskov
    0.86
    tagHelperRunner
    0.85
     ویکی‌پدیا
    0.82
    Rhestr
    0.75
    tvguidetime
    0.75
     FetchType
    0.73
    MLLoader
    0.71
    MessageOf
    0.71
    Activations Density 7.094%

    No Known Activations