© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34690
    Prev
    Next
    INDEX
    Explanations

    solve for x or y

    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_3_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
     сучас
    0.62
    us
    0.61
    s
    0.59
    sword
    0.59
    src
    0.57
     तरह
    0.57
    sw
    0.57
     Наши
    0.55
     χρήση
    0.54
    发达
    0.54
    POSITIVE LOGITS
    ية
    0.87
    га
    0.77
    。\
    0.77
    =\
    0.71
    camping
    0.70
    ку
    0.70
    。
    0.69
    де
    0.68
    ET
    0.67
     avez
    0.65
    Activations Density 0.002%

    No Known Activations