© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109455
    Prev
    Next
    INDEX
    Explanations

    stalk

    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_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ain
    1.52
    ot
    1.26
    ls
    1.24
    ly
    1.22
    ir
    1.20
    ana
    1.19
    lich
    1.17
    ay
    1.16
    خ
    1.16
    on
    1.16
    POSITIVE LOGITS
    )」
    1.23
    i
    1.22
    ي
    1.21
    ς
    1.17
    ಿ
    1.14
    ে
    1.12
    きた
    1.09
    జేపీ
    1.03
    ることが
    1.02
    ﺘ
    1.02
    Activations Density 0.000%

    No Known Activations