© 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. 203341
    Prev
    Next
    INDEX
    Explanations

    island

    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
    (
    1.48
    is
    1.14
    al
    1.04
    "
    1.02
    ing
    1.01
    ட்சத்திர
    1.01
    ant
    0.98
    as
    0.96
    m
    0.94
     of
    0.94
    POSITIVE LOGITS
    ın
    0.98
    ك
    0.93
    い
    0.91
     in
    0.89
    ků
    0.84
     rationalize
    0.84
    ﻛ
    0.84
    ۰۰
    0.82
    ்
    0.81
     في
    0.80
    Activations Density 0.000%

    No Known Activations