© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120110
    Prev
    Next
    INDEX
    Explanations

    degrees and years

    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_27_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
     luctus
    0.33
     ഒ
    0.33
     ungu
    0.33
     rerum
    0.32
     Mercantile
    0.32
     puh
    0.31
     merken
    0.31
     Lichten
    0.31
    我就
    0.30
     zů
    0.30
    POSITIVE LOGITS
     চিত্র
    0.39
     மற்றும்
    0.36
    闖
    0.36
     сей
    0.36
     melee
    0.35
     চ
    0.35
    ário
    0.34
    ạo
    0.34
    进了
    0.34
    као
    0.34
    Activations Density 0.000%

    No Known Activations