© 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. 46738
    Prev
    Next
    INDEX
    Explanations

    thermistor or coal mass

    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
    0.71
    ॉल
    0.68
    ت
    0.66
    ượ
    0.63
    ﻧ
    0.63
    AN
    0.61
    猢
    0.61
    어야
    0.59
     The
    0.58
    ும்
    0.58
    POSITIVE LOGITS
    ти
    0.63
     działa
    0.62
    дко
    0.57
    daki
    0.56
    s
    0.56
    ↵↵
    0.55
    дный
    0.55
    2
    0.55
    ap
    0.54
     än
    0.54
    Activations Density 0.001%

    No Known Activations