© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61391
    Prev
    Next
    INDEX
    Explanations

    each item individually

    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_2_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
     be
    2.02
     to
    1.85
    ED
    1.52
    to
    1.38
    ES
    1.34
    Во
    1.33
     you
    1.31
    ב
    1.23
     avec
    1.20
    Де
    1.19
    POSITIVE LOGITS
    ти
    1.35
    ip
    1.13
    ill
    1.12
    ла
    1.10
    alon
    1.06
    vention
    0.99
    си
    0.96
    em
    0.94
    et
    0.93
    лини
    0.93
    Activations Density 0.001%

    No Known Activations