© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13167
    Prev
    Next
    INDEX
    Explanations

    text appearing in fixed layouts of a document, such as boilerplate, tables, or headers

    oai_token-act-pair · gemini-2.0-flash

    words with specific prefixes or foreign terms

    np_token-act-pair-logits · gpt-4o-mini

    Non-english text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     समीक्षाओं
    -0.44
     issues
    -0.42
    well
    -0.41
     ent
    -0.41
    Well
    -0.39
     issue
    -0.39
     inflation
    -0.38
    盲
    -0.38
    íg
    -0.37
    évaluateur
    -0.37
    POSITIVE LOGITS
     quitté
    0.75
     coû
    0.73
     nucléaire
    0.72
     tartalomajánló
    0.69
     refusé
    0.68
    Дереккөздер
    0.66
    BagConstraints
    0.65
     avoient
    0.65
     <",
    0.65
     profondément
    0.64
    Activations Density 0.269%

    No Known Activations