© 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. 6209
    Prev
    Next
    INDEX
    Explanations

    code snippets or computer related terms

    oai_token-act-pair · gemini-2.0-flash

    say "in, out, or -"

    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
    LookAnd
    -1.05
    GEBURTSDATUM
    -1.02
    MigrationBuilder
    -1.00
    StoryboardSegue
    -1.00
    Personensuche
    -0.98
     ModelExpression
    -0.94
    expandindo
    -0.88
    :✨
    -0.88
    numerusform
    -0.85
     disambiguazione
    -0.85
    POSITIVE LOGITS
     in
    2.67
     In
    1.41
     в
    1.33
    in
    1.27
    In
    1.27
    ใน
    1.24
     IN
    1.20
     în
    1.18
     dalam
    1.16
     در
    1.13
    Activations Density 4.023%

    No Known Activations