© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153703
    Prev
    Next
    INDEX
    Explanations

    indexed_iter()

    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_23_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
    シフト
    0.39
    ქვთ
    0.39
    assignments
    0.37
     काजल
    0.37
     используя
    0.36
    shifts
    0.35
    包含
    0.35
     藤
    0.35
    ूरी
    0.34
    删除
    0.34
    POSITIVE LOGITS
     (%)
    0.44
     subsec
    0.44
     oper
    0.43
     compra
    0.42
     ascends
    0.42
     esti
    0.42
     eos
    0.41
     ascended
    0.41
     enviable
    0.41
    cial
    0.41
    Activations Density 0.000%

    No Known Activations