© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45427
    Prev
    Next
    INDEX
    Explanations

    unicorn horn

    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
     problemat
    0.27
     जरुरत
    0.25
     opcion
    0.24
     Problem
    0.24
     Computation
    0.24
     ٢
    0.24
     निकला
    0.24
     Political
    0.23
     PROCESS
    0.23
    ximation
    0.23
    POSITIVE LOGITS
    yki
    0.23
    Share
    0.22
    रीन
    0.22
    肺
    0.22
    Avec
    0.22
    Uuid
    0.22
    继承
    0.22
     inherits
    0.21
    Nas
    0.21
    eksi
    0.21
    Activations Density 0.011%

    No Known Activations