© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110170
    Prev
    Next
    INDEX
    Explanations

    plain language

    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_2_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
     for
    1.45
     a
    1.44
    т
    1.30
    is
    1.23
    ث
    1.16
     on
    1.11
    ло
    1.08
    á
    1.03
    for
    1.02
    ب
    1.01
    POSITIVE LOGITS
    d
    1.31
    h
    1.30
    től
    1.28
    dan
    1.20
    ری
    1.16
    dad
    1.16
    ﺔ
    1.16
    Count
    1.14
    dar
    1.13
    dates
    1.12
    Activations Density 0.002%

    No Known Activations