© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141802
    Prev
    Next
    INDEX
    Explanations

    craftsmanship, stitching, shoe-making

    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_12_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
     靴
    0.19
    shoes
    0.18
    size
    0.17
    shoe
    0.16
     fär
    0.16
     చేసుకోవ
    0.16
     shoes
    0.16
     दैट
    0.16
    tható
    0.16
     giày
    0.16
    POSITIVE LOGITS
    یر
    0.16
    '
    0.16
     aveva
    0.15
    ian
    0.15
     avuto
    0.15
     hadden
    0.15
     Doyle
    0.15
     конца
    0.15
    しても
    0.14
    らの
    0.14
    Activations Density 0.001%

    No Known Activations