© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261403
    Prev
    Next
    INDEX
    Explanations

    around the

    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_5_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
    一
    1.19
    a
    1.13
    u
    1.11
    r
    1.10
     incentiv
    1.05
    为了
    1.03
    O
    1.00
    し
    0.95
    对
    0.95
    在地
    0.94
    POSITIVE LOGITS
    ла
    2.25
    ية
    1.49
    ри
    1.40
    ль
    1.34
     can
    1.29
    רו
    1.25
    。
    1.23
    ли
    1.21
    ।
    1.20
    ري
    1.13
    Activations Density 0.000%

    No Known Activations