© 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. 120412
    Prev
    Next
    INDEX
    Explanations

    file type selectors

    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
    comers
    0.39
     yp
    0.38
    ionate
    0.37
    费
    0.36
     noticeable
    0.36
     NCA
    0.36
     पाल
    0.36
     unsatisfactory
    0.36
     employment
    0.35
    Employment
    0.35
    POSITIVE LOGITS
     выстав
    0.38
     bekannten
    0.38
    весто
    0.38
    ത്തിയ
    0.37
     मर्ज
    0.37
    ahui
    0.37
    넝
    0.37
    可知
    0.37
     wherever
    0.36
     ممن
    0.36
    Activations Density 0.001%

    No Known Activations