© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260942
    Prev
    Next
    INDEX
    Explanations

    "seriously though"

    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_10_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
     wasn
    0.43
     مب
    0.40
     сма
    0.40
    不敢
    0.39
    CNC
    0.39
     ش
    0.39
     Prud
    0.39
     ശ്രമ
    0.39
     CNC
    0.39
     FYI
    0.39
    POSITIVE LOGITS
    idla
    0.47
    ceived
    0.45
     gini
    0.45
    contiguous
    0.44
    angun
    0.44
     보면은
    0.43
    क़्त
    0.42
    唝
    0.42
     grievance
    0.41
    streets
    0.40
    Activations Density 0.001%

    No Known Activations