© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50100
    Prev
    Next
    INDEX
    Explanations

    того стоит

    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_10_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
    on
    0.68
    ou
    0.60
    aj
    0.57
    ب
    0.56
    م
    0.55
    og
    0.55
    ag
    0.54
    ail
    0.52
    im
    0.52
    away
    0.51
    POSITIVE LOGITS
     Hassel
    0.59
    もっと
    0.56
    ྙ
    0.53
    𒄀
    0.51
     Kun
    0.51
    従って
    0.50
     BER
    0.50
    人も
    0.50
     skeptical
    0.49
    ᱭ
    0.49
    Activations Density 0.000%

    No Known Activations