© 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. 261333
    Prev
    Next
    INDEX
    Explanations

    for each

    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
    S
    1.26
    G
    1.26
    a
    1.22
    k
    1.22
    B
    1.20
    P
    1.20
    H
    1.19
    U
    1.13
     és
    1.11
    n
    1.09
    POSITIVE LOGITS
    ش
    1.63
    ما
    1.56
     to
    1.49
    ق
    1.45
    ス
    1.38
    ر
    1.35
    ح
    1.28
    ב
    1.27
    ون
    1.27
    ات
    1.26
    Activations Density 0.000%

    No Known Activations