© 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. 106678
    Prev
    Next
    INDEX
    Explanations

    intersex variations

    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
     a
    1.75
     has
    1.55
     have
    1.48
    re
    1.42
     as
    1.42
     it
    1.40
    ل
    1.38
    on
    1.37
     is
    1.34
    것
    1.34
    POSITIVE LOGITS
    지
    1.57
    мимо
    1.34
    િ
    1.21
    ات
    1.19
    вими
    1.16
     Balliye
    1.13
    ങ്ങൾ
    1.13
    ци
    1.09
    кри
    1.09
    이었
    1.07
    Activations Density 0.000%

    No Known Activations