© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    say ">"

    np_max-act-logits · gemini-2.5-flash-lite
    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
    Stuff
    0.78
     supersymmetry
    0.78
    Ő
    0.75
     homozyg
    0.73
    Giant
    0.72
    ruf
    0.70
     मंडल
    0.70
    Presentation
    0.69
    ಬ್ಬಳ್ಳಿ
    0.68
    foam
    0.68
    POSITIVE LOGITS
    멜
    0.65
     ലോ
    0.64
     컴
    0.63
     ROOM
    0.61
     दी
    0.60
     зав
    0.60
     въ
    0.59
     फ्र
    0.59
    隂
    0.58
    ൦
    0.58
    Activations Density 0.001%

    No Known Activations