© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13236
    Prev
    Next
    INDEX
    Explanations

    introduction or intro

    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_13_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
    re
    0.49
    çal
    0.47
    de
    0.45
    a
    0.45
    create
    0.44
    /
    0.44
    지를
    0.43
    Pers
    0.43
    d
    0.42
    و
    0.42
    POSITIVE LOGITS
     cerrado
    0.49
     temas
    0.45
     attacking
    0.45
     contraindicated
    0.44
    ায়ন
    0.43
     fermé
    0.43
     antihist
    0.43
     parked
    0.42
     markedly
    0.42
     изоли
    0.42
    Activations Density 0.001%

    No Known Activations