© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8874
    Prev
    Next
    INDEX
    Explanations

    bit, field, encryption, private, prime

    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_13_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
     -
    0.22
     व
    0.21
    atio
    0.20
     فر
    0.19
    bump
    0.19
    Bump
    0.19
     الرغم
    0.18
     Bump
    0.18
    ⋄
    0.18
    ปฏิ
    0.18
    POSITIVE LOGITS
     kullanılır
    0.26
     kullanılan
    0.26
     আপনারা
    0.23
     amacı
    0.23
     aata
    0.22
     herkes
    0.22
    SCUS
    0.22
    nage
    0.22
    OAc
    0.21
    َص
    0.21
    Activations Density 0.006%

    No Known Activations