© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155936
    Prev
    Next
    INDEX
    Explanations

    in

    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_50_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
    otek
    0.38
    ampled
    0.38
     छ
    0.36
     sph
    0.36
     일을
    0.36
    يل
    0.35
    нак
    0.35
    ുകയാണ്
    0.35
    ্রিক
    0.34
    ালো
    0.34
    POSITIVE LOGITS
    恩
    0.45
     Oli
    0.42
    Don
    0.42
    Bob
    0.41
    Extras
    0.40
    ビリ
    0.39
    venues
    0.39
    Ethn
    0.39
     Bibi
    0.38
    XII
    0.38
    Activations Density 0.010%

    No Known Activations