© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7566
    Prev
    Next
    INDEX
    Explanations

    a mix of incomplete phrases that contain a keyword in another language (possibly Croatian)

    oai_token-act-pair · gemini-2.0-flash

    unusual words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     akik
    -0.44
    ChildScrollView
    -0.39
    un
    -0.39
     doGet
    -0.37
     who
    -0.36
    UN
    -0.36
    ார்
    -0.35
    quién
    -0.34
    unic
    -0.33
    }{*}{
    -0.33
    POSITIVE LOGITS
     للاسماء
    0.77
     nahilalakip
    0.73
    shadowOpacity
    0.73
    Tikang
    0.69
    Diwedd
    0.69
    Portály
    0.68
    MigrationBuilder
    0.68
    出版年
    0.67
     houſe
    0.65
     Houſe
    0.63
    Activations Density 0.416%

    No Known Activations