© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210809
    Prev
    Next
    INDEX
    Explanations

    Java, Luzon, East, Jawa

    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_20_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
     Powder
    0.46
    ill
    0.45
    opolitan
    0.45
    irling
    0.45
    -
    0.45
     antagonistic
    0.45
    old
    0.44
     ty
    0.43
    rite
    0.42
     Retrieves
    0.42
    POSITIVE LOGITS
    ленный
    0.50
    はい
    0.46
    สำเร็จ
    0.45
    墉
    0.45
    はや
    0.43
    ણે
    0.42
    ленная
    0.42
    欬
    0.42
    ᒎ
    0.41
    вався
    0.41
    Activations Density 0.000%

    No Known Activations