© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215064
    Prev
    Next
    INDEX
    Explanations

    also followed by a verb

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     -
    0.44
     ---
    0.43
     וא
    0.43
     হারা
    0.41
     而且
    0.41
     —
    0.40
    且
    0.40
    </th>
    0.39
     그리고
    0.39
     존재하는
    0.39
    POSITIVE LOGITS
     internalization
    0.38
    ⅝
    0.38
     filming
    0.37
     talent
    0.37
     mal
    0.36
    াৎ
    0.36
    ður
    0.36
     procuring
    0.36
     chacun
    0.35
    IVIDUAL
    0.35
    Activations Density 0.002%

    No Known Activations