© 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. 59244
    Prev
    Next
    INDEX
    Explanations

    SVN Strategy

    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
    and
    1.32
    ých
    1.16
    ha
    1.07
    has
    1.04
    鄱
    1.04
    ก
    1.00
    was
    0.99
    were
    0.98
    8
    0.97
     by
    0.96
    POSITIVE LOGITS
    -
    1.06
    <unused2172>
    1.04
     étudier
    1.03
    ’
    0.97
    хід
    0.95
     άλλ
    0.94
     élections
    0.94
     étudi
    0.93
    お客
    0.93
     enquête
    0.92
    Activations Density 0.000%

    No Known Activations