© 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. 154647
    Prev
    Next
    INDEX
    Explanations

    family and group members

    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
    Negative Logits
    getProgress
    0.39
    霄
    0.38
     PRET
    0.37
     Noi
    0.37
    𝙵
    0.36
     பொ
    0.36
    )."
    0.35
     ＜
    0.35
     kuin
    0.35
    ?—
    0.35
    POSITIVE LOGITS
    ett
    0.42
    nocześnie
    0.40
     الوزراء
    0.39
     myself
    0.39
    Hosted
    0.39
    Constraint
    0.39
    lesh
    0.38
     خودم
    0.38
    ទទួល
    0.37
    我自己
    0.37
    Activations Density 0.001%

    No Known Activations