© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2378
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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_40_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
     resident
    0.36
    gada
    0.36
     Yol
    0.36
    涿
    0.36
    ერი
    0.35
    म्प
    0.35
    லக
    0.35
    ermo
    0.35
     வடிவ
    0.35
    hael
    0.34
    POSITIVE LOGITS
    ．
    0.70
    ._
    0.58
    .~
    0.49
    .–
    0.45
    .-
    0.44
    .${
    0.43
    .__
    0.43
    .___
    0.42
    ㆍ
    0.41
    ."))
    0.40
    Activations Density 0.294%

    No Known Activations