© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54565
    Prev
    Next
    INDEX
    Explanations

    date numbers

    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_31_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
     নবাব
    0.40
    Ideas
    0.40
     Canadians
    0.36
    champion
    0.36
    侨
    0.36
     чемпиона
    0.36
     apresentação
    0.36
     Ideas
    0.35
    agence
    0.35
    演奏
    0.35
    POSITIVE LOGITS
     contaminant
    0.41
     Levi
    0.38
     puris
    0.37
     insufficiency
    0.37
    <unused17>
    0.37
     minder
    0.37
    पक्ष
    0.37
     Arik
    0.37
     suffisante
    0.36
     nominal
    0.36
    Activations Density 0.000%

    No Known Activations