© 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. 5291
    Prev
    Next
    INDEX
    Explanations

    many foreign words or non-English characters

    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
    s
    1.48
    ات
    1.38
    х
    1.13
    س
    1.09
    ের
    1.04
     gracefully
    1.01
    ς
    0.97
    ites
    0.95
    ्वेस्ट
    0.95
    сь
    0.95
    POSITIVE LOGITS
     dingen
    1.19
     strs
    1.17
     sortes
    1.17
    𝓉
    1.17
    お客様
    1.12
     Meditation
    1.12
    ∞
    1.12
    ানা
    1.10
    ので
    1.10
    పాటు
    1.10
    Activations Density 0.003%

    No Known Activations