© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193572
    Prev
    Next
    INDEX
    Explanations

    including tasks and items

    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_27_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
     ακόμη
    0.35
    chanical
    0.33
    irst
    0.32
    w
    0.32
     зв
    0.32
    ೂರ್ಣ
    0.32
    u
    0.32
    ူ
    0.31
     hallways
    0.31
     আরো
    0.31
    POSITIVE LOGITS
     selecciona
    0.41
     selezione
    0.40
     extrême
    0.39
     seleção
    0.38
     selecionar
    0.38
     selecion
    0.38
    Frankreich
    0.38
    Selecting
    0.37
     Sélectionnez
    0.37
    为您
    0.37
    Activations Density 0.001%

    No Known Activations