© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18185
    Prev
    Next
    INDEX
    Explanations

    Pilates

    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_15_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
     name
    0.50
     labelled
    0.45
     I
    0.45
     hat
    0.44
     t
    0.44
    നിന്ന്
    0.43
     overtaken
    0.42
     gång
    0.42
     T
    0.41
     sought
    0.41
    POSITIVE LOGITS
     álgebra
    0.66
     cerámica
    0.59
     delicioso
    0.57
    carb
    0.55
    ස්ට
    0.55
     frescos
    0.55
    કિંગ
    0.54
    bo
    0.54
    ເຮັດ
    0.54
     ondul
    0.54
    Activations Density 0.001%

    No Known Activations