© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43104
    Prev
    Next
    INDEX
    Explanations

    total

    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_22_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
     буква
    0.43
     питань
    0.41
     중
    0.41
     Anzahl
    0.41
     merges
    0.40
    ุก
    0.40
     mű
    0.40
     reverts
    0.40
     영향
    0.40
     doPost
    0.40
    POSITIVE LOGITS
     მან
    0.44
     ಒಂದು
    0.41
     considerable
    0.39
    hur
    0.38
     _;
    0.38
     contention
    0.38
    嶙
    0.38
     acostumbr
    0.37
    ydon
    0.37
     तत्कालीन
    0.37
    Activations Density 0.000%

    No Known Activations