© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13395
    Prev
    Next
    INDEX
    Explanations

    health statistics and study methodology descriptions

    oai_token-act-pair · gemini-2.0-flash

    Measurement and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    OrDefault
    -0.61
    CLUDING
    -0.59
     testing
    -0.52
    isEmail
    -0.51
    setof
    -0.50
    DrawerToggle
    -0.48
    
    -0.48
    cine
    -0.47
     Romeo
    -0.46
     depart
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.61
    styleUrls
    0.60
    PhysRev
    0.58
    Kanpo
    0.57
     للاسماء
    0.55
     beginnetje
    0.54
    GEBURTSDATUM
    0.54
    RTLR
    0.53
    rrggbb
    0.53
    TemporalType
    0.52
    Activations Density 4.683%

    No Known Activations