© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9698
    Prev
    Next
    INDEX
    Explanations

    internet chat logs

    oai_token-act-pair · gemini-2.0-flash

    salut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    setVerticalGroup
    -0.70
    ViewFeatures
    -0.69
     snippetHide
    -0.69
     وتسجيلات
    -0.66
     initComponents
    -0.65
    stdc
    -0.63
    AndEndTag
    -0.63
     venons
    -0.62
     InputDecoration
    -0.60
    toggler
    -0.59
    POSITIVE LOGITS
     Stelle
    0.44
    مصادر
    0.44
     Geno
    0.43
    getCell
    0.43
     Tink
    0.43
     mergeFrom
    0.43
    anton
    0.43
    ิว
    0.42
     Burgh
    0.41
     Grit
    0.41
    Activations Density 0.231%

    No Known Activations