© 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. 41474
    Prev
    Next
    INDEX
    Explanations

    Brandenburger Tor, Cathedral, new lens

    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
    지
    0.91
    мо
    0.88
    1
    0.78
    0
    0.76
    mc
    0.70
    𝘴
    0.68
    रा
    0.67
     tentang
    0.67
    nc
    0.66
    𝘨
    0.66
    POSITIVE LOGITS
    '
    1.37
    h
    0.98
    ar
    0.97
    ol
    0.90
    é
    0.87
    k
    0.77
    ل
    0.77
    ל
    0.72
    (“
    0.71
    (
    0.70
    Activations Density 0.007%

    No Known Activations