© 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. 12536
    Prev
    Next
    INDEX
    Explanations

    code blocks with an opening curly brace and associated syntax

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    ()))
    -0.48
    by
    -0.47
    AsUp
    -0.47
     élevées
    -0.46
    لم
    -0.45
    carpus
    -0.45
    ()->
    -0.44
     pode
    -0.43
    ())))
    -0.43
    ::
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.82
     >=",
    0.79
    MLLoader
    0.75
    Koordinaten
    0.68
    RectangleBorder
    0.65
    Ārējās
    0.59
     Theſe
    0.59
    ghold
    0.58
    Fordítás
    0.58
     saites
    0.57
    Activations Density 2.100%

    No Known Activations