© 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. 122916
    Prev
    Next
    INDEX
    Explanations

    Bulbapedia or other specific wikis

    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
    ме
    0.79
    0
    0.79
    ０
    0.72
    lies
    0.71
    djang
    0.71
    ב
    0.69
    siswa
    0.68
    밂
    0.68
    delt
    0.68
    ла
    0.67
    POSITIVE LOGITS
     of
    0.98
     l
    0.79
     that
    0.70
    িকে
    0.66
     parec
    0.65
     efficiently
    0.62
     że
    0.61
     on
    0.60
     endure
    0.60
     can
    0.58
    Activations Density 0.001%

    No Known Activations