© 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. 12446
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and environments, especially those related to the `forest` package for drawing trees.

    oai_token-act-pair · gemini-2.0-flash

    LaTeX documents

    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
    脚注の使い方
    -1.21
     propOrder
    -1.10
     HasFactory
    -1.08
    PreferredItem
    -1.07
    windowFixed
    -1.07
    SharedDtor
    -1.05
    ⓘ
    -1.02
     Roskov
    -0.99
    GEBURTSDATUM
    -0.98
    MigrationBuilder
    -0.97
    POSITIVE LOGITS
    ,
    0.62
     in
    0.56
    (
    0.54
     (
    0.53
    ;
    0.50
     as
    0.50
     an
    0.45
     
    0.43
     on
    0.40
     av
    0.40
    Activations Density 12.176%

    No Known Activations