© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167273
    Prev
    Next
    INDEX
    Explanations

    different audiences or tones

    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_31_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
    ウェア
    0.43
     fancied
    0.43
     stories
    0.43
     sentence
    0.43
     حدیث
    0.42
     invern
    0.41
     weeding
    0.41
    讒
    0.41
     திரும்பி
    0.40
     poems
    0.39
    POSITIVE LOGITS
    竽
    0.38
     ইন্
    0.37
     Particles
    0.37
     olhos
    0.36
     Digital
    0.36
     crianças
    0.35
    Digital
    0.35
     XY
    0.35
     DIGITAL
    0.35
    Certified
    0.35
    Activations Density 0.010%

    No Known Activations