© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130128
    Prev
    Next
    INDEX
    Explanations

    investigate

    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_1_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
     to
    1.63
    ר
    1.61
    ↵
    1.45
     be
    1.29
    ’
    1.26
    т
    1.22
    t
    1.21
     on
    1.16
    ر
    1.16
     for
    1.15
    POSITIVE LOGITS
    1.26
    os
    1.03
    quela
    0.85
     जिसके
    0.84
    that
    0.82
    quele
    0.82
    дного
    0.80
    面膜
    0.80
    Н
    0.80
    ات
    0.79
    Activations Density 0.001%

    No Known Activations