© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92877
    Prev
    Next
    INDEX
    Explanations

    Ско, Ко

    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_60_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
    ل
    0.60
    ल
    0.52
    л
    0.48
    ל
    0.48
    ล
    0.45
     poche
    0.45
    ল
    0.43
     Kopp
    0.42
     سزا
    0.42
    ne
    0.41
    POSITIVE LOGITS
     е
    0.62
     г
    0.47
    е
    0.46
     e
    0.45
     ще
    0.45
     д
    0.45
    тор
    0.44
    ку
    0.44
     Тор
    0.44
    тов
    0.43
    Activations Density 0.000%

    No Known Activations