© 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. 47083
    Prev
    Next
    INDEX
    Explanations

    identifying, analyzing, and assessing risks

    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
    Negative Logits
    at
    0.34
    G
    0.34
    ان
    0.33
     seks
    0.33
                    
    0.33
    Pars
    0.33
    c
    0.33
    2
    0.33
    4
    0.33
     disegnare
    0.32
    POSITIVE LOGITS
     ആയ
    0.35
     flashbacks
    0.31
    ?“
    0.31
     garantías
    0.30
    ологии
    0.30
     рэгістра
    0.30
    henden
    0.29
    avení
    0.29
     создании
    0.29
     стаўкі
    0.28
    Activations Density 0.002%

    No Known Activations