© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84069
    Prev
    Next
    INDEX
    Explanations

    Debian GNU/Linux

    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_23_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
    nq
    0.44
    nT
    0.40
    ier
    0.39
    ing
    0.38
    jq
    0.37
    format
    0.37
    nogo
    0.37
    z
    0.37
     Intellectual
    0.36
    setString
    0.36
    POSITIVE LOGITS
    爱好
    0.49
     అంశ
    0.43
     എല്ലാ
    0.42
    ליה
    0.42
    retching
    0.42
     පො
    0.41
    occurring
    0.41
    דיה
    0.41
    小姐
    0.41
     সর্বনিম্ন
    0.40
    Activations Density 0.001%

    No Known Activations