© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61403
    Prev
    Next
    INDEX
    Explanations

    applied

    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_2_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
     as
    1.48
     on
    1.34
    ক
    1.20
    त
    1.18
    ।
    1.17
    y
    1.16
    ی
    1.16
    。
    1.16
    s
    1.15
    k
    1.15
    POSITIVE LOGITS
    ו
    1.16
    the
    0.97
    ל
    0.94
    om
    0.86
    ায়
    0.82
     जोड़ी
    0.82
    ят
    0.81
    ке
    0.80
     bipartite
    0.77
    на
    0.76
    Activations Density 0.003%

    No Known Activations