© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84026
    Prev
    Next
    INDEX
    Explanations

    variable declaration start

    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_23_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
     উপায়
    0.41
    取代
    0.38
    濠
    0.35
    从而
    0.35
     loophole
    0.34
    楼
    0.34
    等等
    0.34
     దగ్
    0.34
     Repeated
    0.33
    figur
    0.33
    POSITIVE LOGITS
    provided
    0.39
     weken
    0.39
    收聽
    0.39
    áculo
    0.38
    ៧
    0.38
     dignidad
    0.38
     séptimo
    0.37
    ាស់
    0.37
    통령
    0.37
    hai
    0.36
    Activations Density 0.000%

    No Known Activations