© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82302
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ت
    2.59
    t
    2.36
    en
    2.06
    م
    1.95
    us
    1.77
    l
    1.75
    is
    1.74
    ل
    1.68
    em
    1.66
     on
    1.65
    POSITIVE LOGITS
     окно
    1.53
    ﺪ
    1.51
    もの
    1.32
    ﻚ
    1.32
    த்ரே
    1.31
    値
    1.31
     consolid
    1.27
    上記の
    1.27
    ເພດ
    1.27
     atteinte
    1.27
    Activations Density 0.000%

    No Known Activations