© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80908
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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_53_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
    quan
    0.46
    chi
    0.43
    ercus
    0.42
    Ț
    0.42
    şte
    0.41
    ठे
    0.41
    ราช
    0.39
     săn
    0.39
     dum
    0.38
    şan
    0.38
    POSITIVE LOGITS
    лія
    0.39
    KOM
    0.36
    ёл
    0.35
    windigkeit
    0.35
    牥
    0.35
     anybody
    0.34
     Anybody
    0.34
    Musik
    0.34
    柄
    0.34
     cytok
    0.34
    Activations Density 0.000%

    No Known Activations