© 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. 203842
    Prev
    Next
    INDEX
    Explanations

    whispering

    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
    ก
    1.25
    тел
    1.18
    ки
    1.13
     antiguo
    1.09
     agave
    1.09
    е
    1.09
     epicenter
    1.08
    ક
    1.07
    о
    1.06
    נ
    1.05
    POSITIVE LOGITS
    a
    1.56
    et
    1.45
    in
    1.42
    ge
    1.31
    the
    1.24
    e
    1.23
    u
    1.11
    _
    1.08
    an
    1.07
    i
    1.06
    Activations Density 0.001%

    No Known Activations