© 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. 178553
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    łach
    0.46
     _{\
    0.43
    ileno
    0.42
     مند
    0.41
     በፍ
    0.39
     ليك
    0.39
     diel
    0.39
    ليف
    0.39
     \,\
    0.38
    筠
    0.38
    POSITIVE LOGITS
     Alliance
    0.42
     гене
    0.41
     Winn
    0.40
     Winston
    0.40
    swe
    0.39
     Auburn
    0.39
    jima
    0.39
    Gene
    0.39
    Swe
    0.38
     MARK
    0.38
    Activations Density 0.000%

    No Known Activations