© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6241
    Prev
    Next
    INDEX
    Explanations

    phrases that describe rankings or orders, especially when they are related to achievements or historical events.

    oai_token-act-pair · gemini-2.0-flash

    crime, degrees, relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    исленность
    -0.81
     InputDecoration
    -0.78
    bootstrapcdn
    -0.75
    EndContext
    -0.71
    migrationBuilder
    -0.71
    Diweddarwch
    -0.69
    SharedDtor
    -0.67
    GraphicsUnit
    -0.65
     CascadeType
    -0.65
    oa̍t
    -0.65
    POSITIVE LOGITS
     first
    1.95
     second
    1.82
    first
    1.80
     First
    1.67
    second
    1.66
    First
    1.63
    Second
    1.62
     Second
    1.61
    FIRST
    1.50
     FIRST
    1.48
    Activations Density 1.938%

    No Known Activations