© 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-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196281
    Prev
    Next
    INDEX
    Explanations

    map and dictionary declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_26_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
     ৭৮
    0.49
    ನ
    0.48
    नं
    0.48
    är
    0.47
    ın
    0.47
    ນະ
    0.46
    nij
    0.45
     councils
    0.45
    uksen
    0.45
    ناد
    0.45
    POSITIVE LOGITS
    0.43
    كيت
    0.42
     sekar
    0.42
    固定
    0.42
     Tef
    0.41
     granola
    0.41
    &$\
    0.41
     Grail
    0.40
    手机
    0.39
    狂
    0.39
    Activations Density 0.000%

    No Known Activations