© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11077
    Prev
    Next
    INDEX
    Explanations

    information about pubs, particularly their names, history, and status.

    oai_token-act-pair · gemini-2.0-flash

    Public locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     cafes
    -0.51
     gyhoeddwyd
    -0.50
    جستارهای
    -0.47
     cafés
    -0.46
    Scope
    -0.46
     mba
    -0.45
    Conway
    -0.44
    cardo
    -0.44
     suí
    -0.44
    CppCodeGen
    -0.44
    POSITIVE LOGITS
     public
    0.68
     gynhyrchwyd
    0.65
     PUBLIC
    0.62
    awaiter
    0.61
    SequentialGroup
    0.60
    AnimationsModule
    0.60
     autorytatywna
    0.60
     Public
    0.60
     opérateur
    0.59
    IsContent
    0.58
    Activations Density 2.131%

    No Known Activations