© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213985
    Prev
    Next
    INDEX
    Explanations

    GTD

    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_5_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
    ка
    1.13
     horrible
    0.94
     tangy
    0.90
     iedereen
    0.86
    ;
    0.86
     whatnot
    0.83
     an
    0.82
     detour
    0.82
    в
    0.82
     docile
    0.81
    POSITIVE LOGITS
    し
    1.41
    ي
    1.31
    ৫
    1.27
    ol
    1.23
    اس
    1.23
    o
    1.23
    しみ
    1.20
    i
    1.17
    بر
    1.16
    oC
    1.15
    Activations Density 0.000%

    No Known Activations