© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80130
    Prev
    Next
    INDEX
    Explanations

    WZ followed by Pr

    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_0_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
    ’
    1.49
    ↵↵
    1.27
    기
    1.18
    ↵
    1.16
     is
    1.15
     on
    1.14
    ิ
    1.14
     was
    1.10
     that
    1.07
    éri
    1.07
    POSITIVE LOGITS
    in
    1.50
    도
    1.30
    も
    1.25
    ة
    1.23
    在
    1.23
    ב
    1.23
    および
    1.20
    ۳
    1.19
    ে
    1.18
     மற்றும்
    1.17
    Activations Density 0.000%

    No Known Activations