© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46183
    Prev
    Next
    INDEX
    Explanations

    meets required standards

    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_22_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
     Сред
    0.38
     கட்டமை
    0.38
     inconsistency
    0.38
    valueChanged
    0.37
     服务
    0.36
    נען
    0.36
     کمار
    0.36
    ₆
    0.36
    narr
    0.36
     hated
    0.35
    POSITIVE LOGITS
    Three
    0.38
     convictions
    0.36
    крема
    0.35
     simp
    0.33
     Kih
    0.33
    Re
    0.33
     peringkat
    0.33
    રો
    0.32
     Wix
    0.32
    Bit
    0.32
    Activations Density 0.007%

    No Known Activations