© 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. 15683
    Prev
    Next
    INDEX
    Explanations

    non-English text or specific characters from non-English languages.

    oai_token-act-pair · gemini-2.0-flash

    non-english language

    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
    ScopeManager
    -0.60
    ஐ
    -0.55
    기를
    -0.53
    을
    -0.53
    を
    -0.52
    devamını
    -0.50
    Revenir
    -0.50
    Kaynakça
    -0.49
     को
    -0.49
    agot
    -0.49
    POSITIVE LOGITS
     виправивши
    0.79
    ibouti
    0.63
    ItemBackground
    0.60
     AssemblyTitle
    0.57
    Zeneca
    0.57
    jsonwebtoken
    0.56
    ElementException
    0.56
    ografija
    0.56
    NUMX
    0.55
    ungkinan
    0.55
    Activations Density 0.356%

    No Known Activations