© 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. 13893
    Prev
    Next
    INDEX
    Explanations

    words related to food consumption and health, and personal pronouns.

    oai_token-act-pair · gemini-2.0-flash

    Habits and health

    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
    Viitteet
    -0.49
     Gazetteer
    -0.48
    Serviço
    -0.47
     scorers
    -0.47
     Connect
    -0.44
     Sali
    -0.42
    شهاد
    -0.42
     Behold
    -0.42
    seido
    -0.42
    Vlast
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.90
     ModelExpression
    0.79
    RegressionTest
    0.73
    intios
    0.72
     للمعارف
    0.72
    tagHelperRunner
    0.69
    IsMutable
    0.69
    ГЛА
    0.68
    IndentedString
    0.63
    LookAnd
    0.62
    Activations Density 3.024%

    No Known Activations