© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2341
    Prev
    Next
    INDEX
    Explanations

    negations combined with technical language related to science

    oai_token-act-pair · gemini-2.0-flash

    words related to limitation or restriction

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

    limitations/restrictions

    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
    RectangleBorder
    -0.79
     onOptions
    -0.75
    Попис
    -0.64
    UnusedPrivate
    -0.61
    يميديا
    -0.58
     ExecuteAsync
    -0.56
    parsedMessage
    -0.55
    createTextNode
    -0.54
     AssemblyCompany
    -0.54
    tonsoft
    -0.54
    POSITIVE LOGITS
     limited
    2.86
     restricted
    2.56
    limited
    2.53
    Limited
    2.44
     Limited
    2.39
     LIMITED
    2.17
     Restricted
    2.14
     confined
    2.13
    restricted
    2.08
    LIMITED
    1.85
    Activations Density 3.979%

    No Known Activations