© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241856
    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_40_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
     feats
    0.44
    urazione
    0.35
    (/^\
    0.34
    agon
    0.34
    ဂျ
    0.34
    ahanam
    0.34
    ಶ್ಚ
    0.34
    erys
    0.34
    шкан
    0.34
    աջ
    0.33
    POSITIVE LOGITS
     हिंसा
    0.42
     Self
    0.40
     Dolphin
    0.40
    抽
    0.40
     Witten
    0.39
    强化
    0.39
     Sprinkle
    0.38
     inhaled
    0.38
    शीर
    0.38
     पार्ट्स
    0.37
    Activations Density 0.000%

    No Known Activations