© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67959
    Prev
    Next
    INDEX
    Explanations

    Nat / Nate names

    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_51_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
     मस
    0.45
    oxide
    0.44
    ogs
    0.39
     صالح
    0.39
    ioxide
    0.37
    मस
    0.37
    дка
    0.37
    ໕
    0.37
    reg
    0.36
    ẹo
    0.36
    POSITIVE LOGITS
     Lap
    0.43
    destroyEach
    0.43
     Sparrow
    0.38
     lap
    0.38
    Lap
    0.38
     Sep
    0.37
     Magnitude
    0.37
    โ
    0.37
    हारा
    0.36
    Jackie
    0.36
    Activations Density 0.000%

    No Known Activations