© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6688
    Prev
    Next
    INDEX
    Explanations

    delimiters like commas and periods, as well as words like "and", when surrounded by food reviews

    oai_token-act-pair · gemini-2.0-flash

    food reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     nahilalakip
    -0.76
     للاسماء
    -0.68
    脚注の使い方
    -0.67
    AddHtmlAttribute
    -0.63
    TestBed
    -0.60
    COUVER
    -0.59
    codable
    -0.59
     Unsc
    -0.58
     }{@
    -0.57
     Gör
    -0.56
    POSITIVE LOGITS
    asserole
    0.53
     Himo
    0.50
    yakit
    0.49
    ederen
    0.44
     sèche
    0.44
    rebbero
    0.43
     Keyes
    0.43
    hearsed
    0.43
     htons
    0.43
    addAction
    0.42
    Activations Density 1.088%

    No Known Activations