© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10204
    Prev
    Next
    INDEX
    Explanations

    content from manuals, instructions or product descriptions

    oai_token-act-pair · gemini-2.0-flash

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    يميديا
    -0.57
    примеча
    -0.55
     faudrait
    -0.55
    locaust
    -0.54
    calar
    -0.54
    offsetof
    -0.54
    ésultat
    -0.54
     consultato
    -0.53
    IsContent
    -0.53
     ChromeDriver
    -0.53
    POSITIVE LOGITS
    はじめに
    0.60
    PerformLayout
    0.49
    knex
    0.47
    '>{
    0.46
    Question
    0.45
    IndentedString
    0.45
     Besar
    0.45
    oredCriteria
    0.44
     sade
    0.43
     voluto
    0.43
    Activations Density 1.626%

    No Known Activations