© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38748
    Prev
    Next
    INDEX
    Explanations

    ajo colorao, just

    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_3_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
    ır
    1.14
    د
    0.94
    ва
    0.92
     (
    0.88
    daki
    0.86
    dı
    0.86
     can
    0.84
    dü
    0.84
    ाई
    0.84
    های
    0.82
    POSITIVE LOGITS
    0
    1.06
    <0x0D>
    1.05
    ка
    0.88
    7
    0.83
    The
    0.79
    4
    0.79
    9
    0.73
    ories
    0.73
    5
    0.70
    %，
    0.70
    Activations Density 0.000%

    No Known Activations