© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193146
    Prev
    Next
    INDEX
    Explanations

    MikroORM module, brick houses, fused silica, anatomy

    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_4_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
    гия
    0.60
    𝔪
    0.54
    gazebo
    0.52
     ขอ
    0.51
    ਕੇ
    0.51
    timevals
    0.50
     clube
    0.48
    ੪
    0.48
    ал
    0.48
     वॉ
    0.48
    POSITIVE LOGITS
     on
    0.60
     disappear
    0.49
     faded
    0.49
    ;
    0.48
     onto
    0.47
     vanishing
    0.47
     impost
    0.46
     with
    0.46
     flames
    0.46
     disappears
    0.46
    Activations Density 0.000%

    No Known Activations