© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39040
    Prev
    Next
    INDEX
    Explanations

    То густо, то пусто

    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_11_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
    )//
    0.37
    Х
    0.37
    б
    0.36
    ఞ
    0.34
    Хо
    0.34
    )<
    0.33
     Conver
    0.33
    聾
    0.33
    ನ್
    0.33
     NEG
    0.33
    POSITIVE LOGITS
    oyan
    0.34
    ä
    0.32
    า
    0.32
    romat
    0.32
    ate
    0.32
    arrant
    0.31
    oya
    0.31
    ecd
    0.31
    annon
    0.31
    াড়ি
    0.31
    Activations Density 0.003%

    No Known Activations