© 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. 8993
    Prev
    Next
    INDEX
    Explanations

    slang terms, especially when used in compound words or phrases

    oai_token-act-pair · gemini-2.0-flash

    mixed or derogatory terms in text

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

    willy

    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
    styleType
    -1.09
    featureID
    -1.06
     '\\;'
    -0.99
     الرياضيه
    -0.99
     للاسماء
    -0.97
    QMetaType
    -0.96
    tagHelperRunner
    -0.93
    MLLoader
    -0.91
    SharedCtor
    -0.91
     كومونز
    -0.90
    POSITIVE LOGITS
    r
    0.45
    -
    0.43
    ,
    0.43
    S
    0.42
     ad
    0.42
     to
    0.42
    <sup>
    0.42
    ad
    0.41
    Ad
    0.40
    .
    0.39
    Activations Density 1.020%

    No Known Activations