© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131085
    Prev
    Next
    INDEX
    Explanations

    Showtime, Showdown, Show Business

    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_1_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
    ל
    1.48
    ת
    1.46
    y
    1.41
    ra
    1.33
    ו
    1.26
    ت
    1.23
    n
    1.18
    k
    1.17
    ro
    1.16
    ল
    1.07
    POSITIVE LOGITS
     in
    1.61
     of
    1.38
     and
    1.27
    ได้
    1.14
     were
    1.10
    주
    1.10
     can
    1.07
    al
    1.05
    ць
    1.05
     decentral
    1.05
    Activations Density 0.002%

    No Known Activations