© 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. 62696
    Prev
    Next
    INDEX
    Explanations

    technical and business terms

    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
    足
    1.86
     foot
    1.34
     Foot
    1.31
     足
    1.29
    Foot
    1.25
    foot
    1.22
    合
    1.12
    FOOT
    1.09
     FOOT
    1.06
    足を
    0.95
    POSITIVE LOGITS
    振
    0.52
    嘉
    0.51
    矩
    0.48
    架
    0.46
    延
    0.46
    象
    0.45
     校
    0.40
     美
    0.39
    毫
    0.38
    Jackson
    0.38
    Activations Density 0.008%

    No Known Activations