© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108548
    Prev
    Next
    INDEX
    Explanations

    top ranking or topology

    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
    ла
    1.40
    ,
    1.23
    ia
    1.19
    -
    1.17
    ை
    1.17
    í
    1.11
    个
    1.10
    er
    1.05
    el
    1.05
    och
    1.05
    POSITIVE LOGITS
    この
    1.25
     on
    1.22
    どう
    1.22
     at
    1.14
    ありません
    1.12
    求め
    1.09
     ری
    1.09
     この
    1.08
    ！)
    1.06
     have
    1.05
    Activations Density 0.001%

    No Known Activations