© 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. 214441
    Prev
    Next
    INDEX
    Explanations

    Mister

    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
     arc
    0.43
     ഡ
    0.40
     са
    0.40
     Dann
    0.39
     flanked
    0.39
    рованы
    0.39
    heil
    0.38
     malle
    0.38
     проекты
    0.38
    πού
    0.38
    POSITIVE LOGITS
    ostok
    0.40
    वेयर
    0.39
    Prof
    0.38
    elands
    0.37
    ʊ
    0.37
     સૂ
    0.37
    ॐ
    0.36
    WG
    0.36
    esini
    0.36
    Oh
    0.36
    Activations Density 0.000%

    No Known Activations