© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4909
    Prev
    Next
    INDEX
    Explanations

    hyphens and emoticons in running text and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act-logits · gemini-2.0-flash

    -

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ed
    -0.78
    ej
    -0.73
    eb
    -0.73
    ei
    -0.73
    eth
    -0.72
    et
    -0.71
    ec
    -0.71
    em
    -0.69
    ep
    -0.69
    ez
    -0.68
    POSITIVE LOGITS
    indépendance
    0.78
    exécution
    0.77
    équipement
    0.76
    hygiène
    0.76
    émission
    0.73
    entraînement
    0.73
    humidité
    0.72
    hébergement
    0.72
    extérieur
    0.72
    assemblée
    0.71
    Activations Density 18.014%

    No Known Activations