© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18838
    Prev
    Next
    INDEX
    Explanations

    names that speak / act

    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_34_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
    他說
    0.44
    他说
    0.40
     歩
    0.35
    冷
    0.35
     holl
    0.34
    냉
    0.34
     규모
    0.33
    lvl
    0.33
     ሂ
    0.32
     EnglishChoose
    0.32
    POSITIVE LOGITS
    вля
    0.36
    ECUT
    0.35
     must
    0.34
    yecto
    0.34
    椎
    0.33
    riter
    0.33
    uffix
    0.33
    ves
    0.32
    BY
    0.32
    operatorname
    0.32
    Activations Density 0.014%

    No Known Activations