© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78362
    Prev
    Next
    INDEX
    Explanations

    resources for

    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_29_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
    スピ
    0.41
    Enhanced
    0.39
     общения
    0.39
    活動
    0.38
    ็ค
    0.38
     разговари
    0.38
    愭
    0.38
     обо
    0.38
    
    0.37
     Га
    0.37
    POSITIVE LOGITS
     seemed
    0.42
     didn
    0.41
     didnt
    0.39
     appunto
    0.38
     not
    0.38
     consumed
    0.38
     skipped
    0.37
     graduation
    0.37
     stanie
    0.37
     seems
    0.36
    Activations Density 0.021%

    No Known Activations