© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 234289
    Prev
    Next
    INDEX
    Explanations

    0

    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
     Bs
    0.43
    drm
    0.42
     zar
    0.40
     రి
    0.40
     bs
    0.39
     維
    0.38
     Victorian
    0.38
     উল
    0.38
    વી
    0.38
    쿨
    0.38
    POSITIVE LOGITS
    跟着
    0.43
    コマンド
    0.42
    ករណ៍
    0.38
    asking
    0.38
    yrus
    0.37
    LastGen
    0.37
    ide
    0.36
    Command
    0.36
    ériel
    0.36
     команди
    0.36
    Activations Density 0.001%

    No Known Activations