© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166671
    Prev
    Next
    INDEX
    Explanations

    feet and fasteners

    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_31_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
     legs
    0.82
     leg
    0.79
     Legs
    0.79
    腿
    0.79
    Leg
    0.70
     Leg
    0.69
    legs
    0.67
    leg
    0.62
     piernas
    0.62
     legg
    0.59
    POSITIVE LOGITS
    Hot
    0.38
    ಉ
    0.37
     ApiException
    0.36
    Checking
    0.35
    TNF
    0.35
    Glo
    0.35
    thern
    0.35
     Clone
    0.34
    SourceRequest
    0.34
    犀
    0.34
    Activations Density 0.018%

    No Known Activations