© 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. 12733
    Prev
    Next
    INDEX
    Explanations

    HTML script tags

    oai_token-act-pair · gemini-2.0-flash

    script-related keywords

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

    /

    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
    #+#
    -0.70
     pleaſure
    -0.62
    /**
    -0.62
    UnknownFieldSet
    -0.60
     Reſ
    -0.59
    TProtocol
    -0.58
    UnknownFields
    -0.57
     juſ
    -0.56
     Diſ
    -0.56
    Blockly
    -0.56
    POSITIVE LOGITS
     يتيمه
    0.63
     мәкал
    0.57
     otomatig
    0.56
     hikariConfig
    0.50
    WithIOException
    0.49
     disambiguazione
    0.48
     ModelExpression
    0.47
     surla
    0.47
    AutoScaleMode
    0.47
    Портал
    0.47
    Activations Density 0.153%

    No Known Activations