© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204786
    Prev
    Next
    INDEX
    Explanations

    yes, good

    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_56_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
    osaur
    0.36
     Dol
    0.36
     કર્યું
    0.35
    ினார்கள்
    0.35
    ctions
    0.35
    теше
    0.34
     kuş
    0.34
    礪
    0.34
    Dol
    0.34
    ^{\#
    0.34
    POSITIVE LOGITS
    好
    2.23
     good
    1.91
    เรีย
    1.88
    好的
    1.84
    good
    1.67
    好了
    1.67
     เรีย
    1.52
     好
    1.45
     tốt
    1.39
     goed
    1.37
    Activations Density 0.002%

    No Known Activations