© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35359
    Prev
    Next
    INDEX
    Explanations

    primed for readiness or candidacy

    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_11_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
     учеб
    0.75
    ن
    0.68
    ন
    0.68
    t
    0.64
    of
    0.60
     tackling
    0.58
     vermelho
    0.58
    ত
    0.57
    ២
    0.57
    کنند
    0.56
    POSITIVE LOGITS
     i
    0.71
     ITV
    0.64
     PGS
    0.59
     करी
    0.57
     antisymmetric
    0.57
    病例
    0.57
     LUC
    0.54
    お願い
    0.53
     I
    0.53
     Fischer
    0.53
    Activations Density 0.002%

    No Known Activations