© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130383
    Prev
    Next
    INDEX
    Explanations

    Ar

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ジ
    0.44
    지
    0.41
    ಜಿ
    0.40
    รวม
    0.39
     Heft
    0.38
     confr
    0.38
     Immunity
    0.38
    cati
    0.37
     রস
    0.37
     Con
    0.36
    POSITIVE LOGITS
    Pg
    0.46
     Pg
    0.42
     pis
    0.41
    adan
    0.41
    spin
    0.40
    鞭
    0.40
    лад
    0.38
    Blake
    0.38
    டக
    0.38
    ad
    0.37
    Activations Density 0.003%

    No Known Activations