© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9224
    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
    딛
    0.73
    ங்கா
    0.72
     składa
    0.68
    iectasis
    0.67
    ރ
    0.66
     सूर्
    0.66
     Come
    0.65
     ba
    0.65
     quantos
    0.64
     найбіль
    0.64
    POSITIVE LOGITS
    形的
    0.73
     तरल
    0.72
    <unused98>
    0.71
     Liquids
    0.70
     रूपों
    0.69
    Logic
    0.68
    ולוג
    0.68
     superintendent
    0.67
    
    0.66
     নরম
    0.65
    Activations Density 0.000%

    No Known Activations