© 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. 18194
    Prev
    Next
    INDEX
    Explanations

    events

    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
    ynh
    0.47
     komunitas
    0.47
    .”[
    0.46
    ⁂
    0.45
    (“
    0.44
    getCode
    0.44
    အပိုင်း
    0.44
    rophe
    0.43
     Kader
    0.43
    pture
    0.42
    POSITIVE LOGITS
    Ту
    0.49
     ojos
    0.45
     ту
    0.45
     custodia
    0.45
     c
    0.44
     v
    0.44
     sur
    0.44
     To
    0.43
     items
    0.43
    弗
    0.43
    Activations Density 0.010%

    No Known Activations