© 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. 148546
    Prev
    Next
    INDEX
    Explanations

    shapes with geometric names

    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
     знают
    0.31
     conocen
    0.31
    aktoren
    0.31
     disguised
    0.29
    ainen
    0.28
     начали
    0.28
     உருவாக்கிய
    0.28
    莆
    0.27
    ัฐ
    0.27
    ៨
    0.27
    POSITIVE LOGITS
    排水
    0.28
    ))=\
    0.28
    鳄
    0.27
     eV
    0.27
    ]_{
    0.26
    _{
    0.26
     tr
    0.25
    )$
    0.25
    =\
    0.25
    স
    0.25
    Activations Density 0.000%

    No Known Activations