© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90084
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    irnya
    0.49
     identities
    0.48
    J
    0.48
    जरी
    0.46
    anya
    0.46
     Identities
    0.44
    Families
    0.44
    anyak
    0.43
    Z
    0.42
    aders
    0.42
    POSITIVE LOGITS
    ➘
    0.55
     هاش
    0.50
    elfde
    0.49
    rieben
    0.48
    dienst
    0.48
    ោ
    0.48
     kha
    0.47
     schrift
    0.47
    洏
    0.46
     يوليو
    0.46
    Activations Density 0.000%

    No Known Activations