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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9316
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सिंगापुर
    0.82
    ാനുള്ള
    0.79
    σότε
    0.73
    >?,
    0.72
     naturalmente
    0.71
     Lampard
    0.71
    istently
    0.70
    inalis
    0.70
    ্যানে
    0.70
     mydict
    0.70
    POSITIVE LOGITS
    FNO
    0.64
    curl
    0.62
    RCC
    0.62
     nine
    0.61
    Fx
    0.61
     taken
    0.61
    fx
    0.60
    㐫
    0.59
    Taken
    0.59
    Copyright
    0.59
    Activations Density 0.001%

    No Known Activations