© 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. 32421
    Prev
    Next
    INDEX
    Explanations

    Tennessee places

    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
     secund
    0.44
    𝗬
    0.43
     mary
    0.42
     TH
    0.42
     Mary
    0.40
    mary
    0.40
    Թ
    0.40
    cepción
    0.39
     MARY
    0.39
    Mary
    0.39
    POSITIVE LOGITS
    Shortcut
    0.38
     जोड़ों
    0.38
    签证
    0.36
     Synt
    0.36
    ございます
    0.34
     Bri
    0.34
    ovies
    0.34
     кри
    0.34
    cant
    0.34
    ミ
    0.34
    Activations Density 0.000%

    No Known Activations