© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132162
    Prev
    Next
    INDEX
    Explanations

    cruiser / cruiservariants

    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_6_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
     it
    1.55
     the
    1.43
    س
    1.43
     for
    1.25
    and
    1.16
    ä
    1.16
    im
    1.16
    ik
    1.14
    it
    1.13
    un
    1.13
    POSITIVE LOGITS
    кна
    0.80
    Ꮺ
    0.79
    рб
    0.76
    сия
    0.72
    )?;
    0.72
    σεων
    0.72
    лни
    0.71
     јед
    0.71
    ্তার
    0.70
    YH
    0.69
    Activations Density 0.000%

    No Known Activations