© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38271
    Prev
    Next
    INDEX
    Explanations

    PART

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     AP
    0.63
    AP
    0.57
    اے
    0.54
    Ａ
    0.52
     AK
    0.50
    AK
    0.46
    )}}{\
    0.46
    AV
    0.46
     एपी
    0.45
    AC
    0.44
    POSITIVE LOGITS
     TI
    0.57
     T
    0.53
    TI
    0.49
     II
    0.47
     TO
    0.47
    III
    0.46
    II
    0.46
     WI
    0.44
     الت
    0.43
     TRANS
    0.42
    Activations Density 0.000%

    No Known Activations