© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 87018
    Prev
    Next
    INDEX
    Explanations

    static files

    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_18_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
     Feuerwehr
    0.54
     :=\
    0.54
     Igreja
    0.52
    )».
    0.50
    }[!
    0.49
    listView
    0.49
     ವೇಳ
    0.48
    ┕
    0.48
     KK
    0.48
    )」
    0.47
    POSITIVE LOGITS
    Life
    0.49
     woman
    0.46
     great
    0.45
    버
    0.45
    This
    0.44
     prestig
    0.44
    ner
    0.44
    add
    0.42
    Woman
    0.42
    new
    0.42
    Activations Density 0.000%

    No Known Activations