© 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. 90277
    Prev
    Next
    INDEX
    Explanations

    list 3-5 key items

    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
     Xiang
    0.41
     Tonga
    0.39
     PDT
    0.38
     MIT
    0.37
     Samo
    0.37
     Kolmogorov
    0.37
     Auf
    0.37
    Rough
    0.36
    Minecraft
    0.36
     ঔ
    0.35
    POSITIVE LOGITS
    బ్ద
    0.43
    くれる
    0.42
    חה
    0.42
    ípios
    0.40
     allege
    0.40
     وفا
    0.40
     geprüft
    0.39
    벗
    0.39
    ﾆ
    0.39
     aliphatic
    0.39
    Activations Density 0.007%

    No Known Activations