© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116177
    Prev
    Next
    INDEX
    Explanations

    input type

    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_27_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
    抗
    0.45
     new
    0.44
     ئەو
    0.44
     Sutton
    0.43
    ​​
    0.40
     newer
    0.39
     جديده
    0.39
    fe
    0.38
    返す
    0.37
     नये
    0.37
    POSITIVE LOGITS
    䢎
    0.39
     کوچک
    0.39
    殳
    0.38
    悹
    0.38
     kaam
    0.38
     PLIST
    0.38
    mdat
    0.37
     можли
    0.37
     часу
    0.37
     स्केल
    0.37
    Activations Density 0.000%

    No Known Activations