© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204645
    Prev
    Next
    INDEX
    Explanations

    HOW

    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_56_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
    Sch
    0.56
    Ap
    0.55
     ap
    0.54
     Ap
    0.52
    L
    0.49
    ی
    0.46
     sch
    0.46
     Sch
    0.45
    ?-
    0.44
     L
    0.42
    POSITIVE LOGITS
     الف
    0.49
     prote
    0.49
    الف
    0.41
     F
    0.40
    crate
    0.40
     Prote
    0.40
    prote
    0.39
     Ф
    0.37
     сообщили
    0.36
     존
    0.36
    Activations Density 0.000%

    No Known Activations