© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11205
    Prev
    Next
    INDEX
    Explanations

    чем больше, тем

    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_13_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
    y
    0.54
    her
    0.51
    et
    0.50
    een
    0.48
    en
    0.47
    in
    0.46
    ées
    0.46
    ism
    0.45
    t
    0.44
    c
    0.44
    POSITIVE LOGITS
    FFEE
    0.53
    INCLUDING
    0.52
     comienza
    0.50
    মুসল
    0.49
    America
    0.48
    夼
    0.47
     wrześ
    0.47
     appraisals
    0.47
    Koch
    0.46
    可能
    0.46
    Activations Density 0.000%

    No Known Activations