© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105755
    Prev
    Next
    INDEX
    Explanations

    Molar 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_1_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
    т
    1.45
    ни
    1.44
    ли
    1.39
    то
    1.23
    ע
    1.23
    س
    1.14
    says
    1.13
    ра
    1.10
    ISTAN
    1.09
    г
    1.08
    POSITIVE LOGITS
    ing
    1.32
     of
    1.25
    of
    0.97
    ;
    0.96
     be
    0.92
     in
    0.92
    ও
    0.88
     digit
    0.86
     well
    0.85
    ة
    0.85
    Activations Density 0.000%

    No Known Activations