© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167287
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     efforts
    0.71
     esfuerzos
    0.64
    尽
    0.62
    努力
    0.61
    全力
    0.61
     endeavours
    0.61
     Efforts
    0.60
     প্রচেষ্টা
    0.57
     upaya
    0.56
     постара
    0.55
    POSITIVE LOGITS
    VERN
    0.38
     pron
    0.35
    afd
    0.35
    Tha
    0.34
     ورد
    0.33
    ើន
    0.33
    )$-
    0.33
    kwik
    0.32
     ইসলামাবাদের
    0.32
    Synt
    0.32
    Activations Density 0.008%

    No Known Activations