© 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. 103301
    Prev
    Next
    INDEX
    Explanations

    super

    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
     in
    1.16
    ,
    1.14
    ه
    1.08
     are
    1.04
    ي
    1.03
     contours
    1.02
     σε
    1.02
     washers
    0.99
     axles
    0.98
     exasper
    0.98
    POSITIVE LOGITS
    ר
    1.24
    0
    1.23
    ')
    1.08
    r
    0.97
    ")
    0.97
    ０
    0.96
    I
    0.96
    نه
    0.89
    ofinstagram
    0.89
    อร์
    0.88
    Activations Density 0.000%

    No Known Activations