© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11019
    Prev
    Next
    INDEX
    Explanations

    code snippets and configuration details, especially related to JSON and web applications

    oai_token-act-pair · gemini-2.0-flash

    say "/"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     
    -0.77
     C
    -0.67
     K
    -0.65
     (
    -0.64
    <eos>
    -0.64
    ,
    -0.63
     D
    -0.62
     A
    -0.62
     F
    -0.60
     V
    -0.59
    POSITIVE LOGITS
     autorytatywna
    1.38
     Efq
    1.17
     kasarigan
    1.17
     itſelf
    1.16
    IsMutable
    1.14
     Monfieur
    1.13
     doubtnut
    1.11
     चीज़ों
    1.09
    AddTagHelper
    1.08
     ModelExpression
    1.08
    Activations Density 2.805%

    No Known Activations