© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5111
    Prev
    Next
    INDEX
    Explanations

    improvisation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ться
    3.19
    تهم
    2.87
    ت
    2.85
    zzel
    2.50
    تف
    2.46
    в
    2.43
     sulit
    2.41
     básicos
    2.38
    '_
    2.38
    ❞
    2.37
    POSITIVE LOGITS
     Appropriations
    2.78
    ated
    2.74
    \}.
    2.69
     isometry
    2.66
     вроде
    2.62
    améliorer
    2.60
    𝗴
    2.58
    certificates
    2.58
    𝗽
    2.58
     HHS
    2.57
    Activations Density 0.007%

    No Known Activations