© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205191
    Prev
    Next
    INDEX
    Explanations

    javascript alert

    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_37_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
     clar
    0.38
     റേ
    0.38
    ABB
    0.38
    歇
    0.36
     nobis
    0.35
    льник
    0.35
    ᓪ
    0.35
    @"
    0.34
    खर
    0.34
     산업
    0.34
    POSITIVE LOGITS
     ballot
    0.38
     शिखर
    0.38
     সুদ
    0.37
     frust
    0.36
     copa
    0.36
     Widodo
    0.36
    је
    0.36
    Bibliografia
    0.36
     soglas
    0.36
     дву
    0.36
    Activations Density 0.000%

    No Known Activations