© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127475
    Prev
    Next
    INDEX
    Explanations

    solar water heating collectors

    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_3_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
    ﺭ
    0.72
    ﻱ
    0.71
     ﺍ
    0.68
    SVM
    0.66
    ICreate
    0.64
    ﺩ
    0.64
    TINGS
    0.63
    SAP
    0.63
    HOUSE
    0.62
    PVC
    0.61
    POSITIVE LOGITS
    sa
    0.73
     света
    0.72
    ك
    0.68
    sm
    0.67
    sede
    0.66
    sz
    0.66
    ر
    0.65
    ن
    0.65
    ご紹介
    0.65
     다르
    0.64
    Activations Density 0.001%

    No Known Activations