© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2574
    Prev
    Next
    INDEX
    Explanations

    code snippets, code syntax and possibly error messages

    oai_token-act-pair · gemini-2.0-flash

    Code related snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Jei
    -0.38
     tää
    -0.38
     puol
    -0.37
     ympä
    -0.35
    intens
    -0.35
     vähän
    -0.33
    effect
    -0.33
    silent
    -0.33
    handle
    -0.33
    Enf
    -0.32
    POSITIVE LOGITS
     متعلقه
    0.71
    kuuta
    0.67
    存于互联网档案馆
    0.63
     kasarigan
    0.60
     الحره
    0.58
     BoxFit
    0.58
    RTEE
    0.56
     ModelExpression
    0.56
     بيها
    0.55
    וויק
    0.54
    Activations Density 3.282%

    No Known Activations