© 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. 46207
    Prev
    Next
    INDEX
    Explanations

    Z prefix for identifiers

    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
    郷
    0.40
    Rather
    0.38
    État
    0.37
    ına
    0.36
    डली
    0.36
    에서의
    0.35
     buah
    0.35
    explorer
    0.35
     típica
    0.35
    ـ
    0.35
    POSITIVE LOGITS
     lectures
    0.38
     vandalism
    0.37
     open
    0.36
     speculation
    0.36
     fools
    0.34
     Clarkson
    0.34
     Tudor
    0.34
     Kalamazoo
    0.33
     security
    0.33
     dishonest
    0.33
    Activations Density 0.001%

    No Known Activations