© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90350
    Prev
    Next
    INDEX
    Explanations

    tro

    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_11_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
    AT
    0.56
    Bạn
    0.56
    您
    0.54
    Có
    0.53
    Dok
    0.53
    AG
    0.52
    Aunque
    0.52
     يجب
    0.52
    𝙄
    0.52
    Gu
    0.51
    POSITIVE LOGITS
    ש
    0.80
    ח
    0.60
    した
    0.60
    ಗರ
    0.56
     myeloid
    0.56
    שית
    0.55
    acre
    0.55
    sensitive
    0.54
     자체
    0.54
    です
    0.53
    Activations Density 0.000%

    No Known Activations