© 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. 9197
    Prev
    Next
    INDEX
    Explanations

    1

    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
    第八
    0.77
    第三
    0.75
     trzec
    0.73
    广播
    0.72
     capitol
    0.68
     üçüncü
    0.68
    െ
    0.68
    빕
    0.67
     третий
    0.66
     broadcasting
    0.66
    POSITIVE LOGITS
     SM
    0.68
    時
    0.67
     sm
    0.64
     Time
    0.63
     时
    0.62
     Four
    0.61
     four
    0.61
    时
    0.60
    sm
    0.60
    Four
    0.59
    Activations Density 0.005%

    No Known Activations