© 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. 110350
    Prev
    Next
    INDEX
    Explanations

    b/w, b/c, b/i, b/l

    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
    ل
    1.94
    л
    1.65
    ल
    1.33
    ל
    1.32
    s
    1.20
    st
    1.18
    لل
    1.18
    ש
    1.16
    G
    1.13
    la
    1.13
    POSITIVE LOGITS
     profiter
    1.01
    ő
    1.01
    ção
    1.00
    ukset
    0.95
    ó
    0.95
     is
    0.95
    ado
    0.93
    8
    0.93
    ation
    0.90
    ция
    0.90
    Activations Density 0.001%

    No Known Activations