© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14518
    Prev
    Next
    INDEX
    Explanations

    mentions of entities involved in roles and contexts.

    oai_token-act-pair · gemini-2.0-flash

    roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Diſ
    -0.68
     Conſ
    -0.67
     Reſ
    -0.63
     role
    -0.63
     Inſ
    -0.60
     poffe
    -0.59
     Perſ
    -0.59
     itſelf
    -0.56
     suom
    -0.55
     Eſ
    -0.53
    POSITIVE LOGITS
    posedge
    0.95
    yntaxException
    0.91
    OGND
    0.82
    AndEndTag
    0.78
     protoimpl
    0.76
    LLocation
    0.75
    MIDDLEWARE
    0.73
     GreatSchools
    0.73
    FTFY
    0.71
     للمعارف
    0.70
    Activations Density 1.604%

    No Known Activations