© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93111
    Prev
    Next
    INDEX
    Explanations

    information gain and lift

    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_11_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
     n
    0.27
     (
    0.25
    ina
    0.23
    ga
    0.23
    n
    0.22
    gg
    0.21
    sa
    0.21
    se
    0.21
    6
    0.21
    ka
    0.20
    POSITIVE LOGITS
    া
    0.21
    лю
    0.19
    াব
    0.19
    ি
    0.19
    ו
    0.18
     মৃত
    0.18
    зак
    0.18
    례
    0.18
    <0xD0>
    0.18
    म्मत
    0.18
    Activations Density 0.003%

    No Known Activations