© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120556
    Prev
    Next
    INDEX
    Explanations

    special characters and structure

    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_27_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
    லோச
    0.33
    prog
    0.32
    zecz
    0.32
     prostitutes
    0.31
     Kursk
    0.29
    motionProxy
    0.29
    Dichloro
    0.29
    檩
    0.29
     competes
    0.29
     handout
    0.29
    POSITIVE LOGITS
    สด
    0.31
    ूह
    0.30
    ノ
    0.30
    nome
    0.30
    白
    0.29
    гі
    0.29
     가장
    0.29
    volve
    0.29
     என்க
    0.29
     Wastewater
    0.29
    Activations Density 0.029%

    No Known Activations