© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156556
    Prev
    Next
    INDEX
    Explanations

    Pumps and pumping

    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_2_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
    l
    1.31
    ۰
    1.18
    ﻡ
    1.09
    adar
    1.06
    (
    1.05
    ิ
    1.04
    ach
    1.02
     It
    1.02
    بھی
    1.02
    il
    1.02
    POSITIVE LOGITS
    на
    1.46
    .
    1.37
    리
    1.33
    я
    1.29
    ла
    1.25
    ك
    1.25
    rt
    1.23
    ला
    1.20
    କ
    1.16
    2
    1.15
    Activations Density 0.001%

    No Known Activations