© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13295
    Prev
    Next
    INDEX
    Explanations

    steps, floor, Kegels, cranes, seeds

    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_13_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
    ällt
    0.58
    id
    0.56
    ENDAR
    0.52
     jär
    0.51
    ogliere
    0.48
     clarifies
    0.48
     menjaga
    0.47
    ò
    0.47
     Hôtel
    0.46
    érieur
    0.46
    POSITIVE LOGITS
    chaoxing
    0.52
     zhu
    0.49
    ఓ
    0.48
    ໂດ
    0.47
     सुमन
    0.47
     prosecutions
    0.47
     执行
    0.47
     houseplants
    0.46
     unvaccinated
    0.46
    㳡
    0.46
    Activations Density 0.029%

    No Known Activations