© 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. 9047
    Prev
    Next
    INDEX
    Explanations

    AWS services

    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
    sitting
    0.73
    óch
    0.73
    ба
    0.70
    黜
    0.70
     sitting
    0.69
    ICAS
    0.69
    рган
    0.68
     ஒ
    0.68
    RICS
    0.67
    رمپ
    0.67
    POSITIVE LOGITS
     तेलु
    0.65
     Joe
    0.63
    ume
    0.61
     मेजब
    0.57
     남
    0.57
     ზ
    0.56
    Joe
    0.54
     amino
    0.53
     computer
    0.53
     ape
    0.53
    Activations Density 0.066%

    No Known Activations