© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12743
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode syntax

    oai_token-act-pair · gemini-2.0-flash

    frac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     
    -1.28
     Efq
    -0.53
    ,:);
    -0.46
    ^(@)
    -0.44
    ontale
    -0.42
    drawal
    -0.42
    〢
    -0.39
    jectures
    -0.39
    %");
    -0.38
    forKey
    -0.37
    POSITIVE LOGITS
    -
    0.82
     متعلقه
    0.71
     jspb
    0.66
    tagHelperRunner
    0.66
    ResumeLayout
    0.64
     وتسجيلات
    0.63
    WriteLiteral
    0.62
    ৮
    0.60
     -
    0.60
     TAMBÉM
    0.59
    Activations Density 2.553%

    No Known Activations