© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227992
    Prev
    Next
    INDEX
    Explanations

    boxing ring, matches, and guard

    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_6_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
    ↵↵
    1.13
    </strong>
    0.94
    ↵↵↵
    0.85
     not
    0.85
     impenetrable
    0.81
    போது
    0.80
    you
    0.79
    )\
    0.77
    }\
    0.76
     הת
    0.76
    POSITIVE LOGITS
    ة
    1.39
    í
    1.28
    า
    1.25
    ور
    1.24
    m
    1.24
    p
    1.17
    ing
    1.16
     (
    1.13
    ü
    1.10
    ina
    1.06
    Activations Density 0.000%

    No Known Activations