© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198531
    Prev
    Next
    INDEX
    Explanations

    sharpness and focus

    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_15_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
    」「
    0.53
     smeared
    0.50
    हान
    0.49
     Ideally
    0.48
     purifying
    0.47
    튀
    0.45
     नौकरियों
    0.44
     smear
    0.44
    ્યે
    0.44
    Ա
    0.44
    POSITIVE LOGITS
     Villanova
    0.57
     पासवान
    0.52
     rück
    0.51
     Newport
    0.50
     THIRD
    0.50
     Debbie
    0.49
     ende
    0.49
     AST
    0.49
     Schrödinger
    0.49
     up
    0.48
    Activations Density 0.003%

    No Known Activations