© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214506
    Prev
    Next
    INDEX
    Explanations

    wide, broad, широ

    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
    다
    1.57
    ai
    1.44
    ل
    1.35
    া
    1.33
    ן
    1.27
    리
    1.27
    ot
    1.21
    é
    1.16
    aw
    1.05
    arg
    1.05
    POSITIVE LOGITS
     the
    1.23
    กับ
    1.19
     entour
    1.18
     acumen
    1.15
     obten
    1.13
    s
    1.11
     aider
    1.09
     amiga
    1.09
     obje
    1.08
     envo
    1.08
    Activations Density 0.000%

    No Known Activations