© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9900
    Prev
    Next
    INDEX
    Explanations

    text enclosed in parentheses, brackets, quote marks, and code symbols, and related legal and financial newswire disclaimers.

    oai_token-act-pair · gemini-2.0-flash

    "e" followed by letter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    indépendance
    -0.69
    émission
    -0.65
    exécution
    -0.64
    humidité
    -0.63
    enfance
    -0.62
    assemblée
    -0.62
    extérieur
    -0.62
    habitude
    -0.62
    entraînement
    -0.61
    équipement
    -0.61
    POSITIVE LOGITS
    ej
    0.73
    eb
    0.72
    ei
    0.69
    eh
    0.68
    ed
    0.68
    eth
    0.68
    ede
    0.66
    ec
    0.66
    et
    0.65
    ech
    0.65
    Activations Density 5.884%

    No Known Activations