© 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. 3117
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and symbols, sometimes when surrounded by numbers

    oai_token-act-pair · gemini-2.0-flash

    word patterns indicating code or programming contexts

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

    calculations

    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
     intptr
    -0.62
    ftagPool
    -0.54
     Ryan
    -0.50
    stdc
    -0.48
    ))]
    -0.46
    ])]
    -0.46
    argout
    -0.46
    iosamente
    -0.45
    getResultList
    -0.45
     ""
    -0.44
    POSITIVE LOGITS
    BASEPATH
    0.63
    ImageContext
    0.60
    adpleegd
    0.59
     تضيفلها
    0.57
    ğraf
    0.57
    Fordítás
    0.57
     ModelExpression
    0.56
    loài
    0.56
    skosten
    0.56
    MethodManager
    0.55
    Activations Density 1.354%

    No Known Activations