© 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. 195156
    Prev
    Next
    INDEX
    Explanations

    URLs with slashes

    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
    isl
    0.52
     tac
    0.45
     نتیجہ
    0.44
     wipe
    0.43
     trouvent
    0.43
     aportan
    0.42
    艶
    0.42
    letic
    0.41
    nig
    0.41
    ous
    0.41
    POSITIVE LOGITS
    $.
    0.52
    }$.
    0.50
     Ovaj
    0.50
     मेघा
    0.50
    РА
    0.49
     ইউনিভার্সি
    0.48
    क्षणिक
    0.47
     Brasília
    0.46
    قية
    0.46
    гана
    0.46
    Activations Density 0.002%

    No Known Activations