© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104223
    Prev
    Next
    INDEX
    Explanations

    upvote, resistance, monitor

    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_1_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
    ли
    1.41
    ק
    1.34
    та
    1.18
    ch
    1.17
    ip
    1.10
    ك
    1.05
    ki
    1.05
    ку
    1.02
     compr
    1.01
    ต
    1.00
    POSITIVE LOGITS
    ו
    1.16
    ोत्सव
    0.93
    ्डा
    0.93
     Kishore
    0.91
    u
    0.90
     Changes
    0.89
     Nahin
    0.88
    ות
    0.85
    ोबर
    0.85
    ަށް
    0.84
    Activations Density 0.000%

    No Known Activations