© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40507
    Prev
    Next
    INDEX
    Explanations

    months

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ль
    0.45
    𝚕
    0.43
    TaskPojo
    0.42
    ⓛ
    0.40
    ЛЬ
    0.40
    楧
    0.38
    tAux
    0.37
    lès
    0.37
    ലി
    0.37
    𝘭
    0.37
    POSITIVE LOGITS
     six
    0.38
     kms
    0.37
     designating
    0.37
     графі
    0.36
     twelve
    0.36
     graphics
    0.35
     currency
    0.35
     escrit
    0.35
    근
    0.35
     fond
    0.35
    Activations Density 0.001%

    No Known Activations