© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207797
    Prev
    Next
    INDEX
    Explanations

    related to screenshots or videos

    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_20_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
     sunflowers
    0.45
     speculate
    0.44
     fdPar
    0.43
     tastefully
    0.43
     भुव
    0.42
    ogh
    0.42
     t
    0.41
     deberán
    0.41
     fingern
    0.41
     saludable
    0.40
    POSITIVE LOGITS
    द्दा
    0.45
    喰
    0.44
    转向
    0.43
    缺乏
    0.42
    BBC
    0.41
    远
    0.40
    商业
    0.40
     Fernandez
    0.40
    ίνη
    0.40
    陷入
    0.40
    Activations Density 0.000%

    No Known Activations