© 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. 34801
    Prev
    Next
    INDEX
    Explanations

    original [token] number

    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
    𝙤
    0.75
    و
    0.73
    osar
    0.71
    牥
    0.68
    㞔
    0.66
    os
    0.65
     sociaux
    0.65
     moistur
    0.64
    ction
    0.64
    مون
    0.64
    POSITIVE LOGITS
     reorgan
    0.73
     diseñ
    0.70
    をして
    0.70
     protesting
    0.68
    1
    0.65
     rescheduled
    0.63
    0
    0.63
     deduced
    0.60
    ;
    0.59
     for
    0.59
    Activations Density 0.020%

    No Known Activations