© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195048
    Prev
    Next
    INDEX
    Explanations

    eye-catching

    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_15_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
    ’
    0.62
    j
    0.58
     receipts
    0.58
    ok
    0.55
     eigenes
    0.54
    ov
    0.53
    rive
    0.52
    og
    0.51
    uc
    0.51
     calories
    0.51
    POSITIVE LOGITS
    כה
    0.51
     త
    0.50
    WeekDates
    0.50
    ήμε
    0.49
    قان
    0.48
     راه
    0.47
     Kras
    0.47
    Koordin
    0.46
    Ꭺ
    0.46
    िता
    0.46
    Activations Density 0.003%

    No Known Activations