© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62247
    Prev
    Next
    INDEX
    Explanations

    verb endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     카
    0.44
     Endocrinol
    0.42
     Niger
    0.40
     โปร
    0.40
     terang
    0.40
    orthogonal
    0.40
    ्रू
    0.39
     返
    0.37
     Endocrinology
    0.37
    XO
    0.37
    POSITIVE LOGITS
    adis
    0.44
    ished
    0.43
    ishes
    0.42
    ilte
    0.40
    ulé
    0.36
    ফান
    0.36
     nour
    0.36
    紊
    0.36
    ishing
    0.36
    িবাস
    0.36
    Activations Density 0.001%

    No Known Activations