© 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. 130188
    Prev
    Next
    INDEX
    Explanations

    mixed content

    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
     рит
    0.44
     Burt
    0.38
    हतक
    0.38
     ryt
    0.38
    скет
    0.38
    സ്ട
    0.38
    楠
    0.37
    ObjectName
    0.36
    焱
    0.36
    ূট
    0.36
    POSITIVE LOGITS
    loz
    0.40
    jera
    0.40
     mark
    0.39
    vili
    0.39
     Gerald
    0.38
    ติด
    0.38
     ویب
    0.38
     giver
    0.38
    vi
    0.38
     میل
    0.37
    Activations Density 0.000%

    No Known Activations