© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205080
    Prev
    Next
    INDEX
    Explanations

    gross

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     لن
    0.37
     nuk
    0.37
    action
    0.37
     acción
    0.36
     ந
    0.36
    rtl
    0.36
     action
    0.36
     ধনী
    0.35
     bal
    0.35
    溶解
    0.34
    POSITIVE LOGITS
    versation
    0.44
     McKenzie
    0.40
    orems
    0.40
    ֿ
    0.37
     Bene
    0.37
    通话
    0.37
    বৃন্দ
    0.36
     सिन
    0.36
    وة
    0.36
     साइनस
    0.35
    Activations Density 0.001%

    No Known Activations