© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102714
    Prev
    Next
    INDEX
    Explanations

    zero-shot classification

    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_16_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
     сучас
    0.66
    🔹
    0.61
     Passo
    0.59
     pliable
    0.58
    iscus
    0.57
    osevelt
    0.57
    ydent
    0.57
     современ
    0.56
    snorkel
    0.56
    órmula
    0.56
    POSITIVE LOGITS
    ت
    0.57
    اک
    0.56
    ना
    0.55
    有
    0.55
    К
    0.55
    اول
    0.55
    ංග
    0.55
     elections
    0.54
    ك
    0.54
    据
    0.54
    Activations Density 0.001%

    No Known Activations