© 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. 6855
    Prev
    Next
    INDEX
    Explanations

    quotation marks and other formatting symbols, especially when associated with political discourse and health-related trials.

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    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
    er
    -0.58
    LY
    -0.51
     pitié
    -0.48
    owiak
    -0.47
    erle
    -0.47
    est
    -0.47
     stället
    -0.47
    ly
    -0.46
    큼
    -0.46
    verständlich
    -0.46
    POSITIVE LOGITS
    DoubleQuotes
    0.58
    ing
    0.57
     AttributeSet
    0.50
    ING
    0.49
    XmlAccessType
    0.48
    ingh
    0.47
    WebElementEntity
    0.45
    inSlope
    0.44
    simpleType
    0.44
     Meksiku
    0.43
    Activations Density 12.327%

    No Known Activations