© 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. 9230
    Prev
    Next
    INDEX
    Explanations

    relationships, analogies, concepts

    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
    W
    0.52
    WL
    0.52
     [@
    0.52
     Blowing
    0.52
    \;
    0.51
     використання
    0.51
     Along
    0.50
     Width
    0.50
     lát
    0.50
     вла
    0.50
    POSITIVE LOGITS
    nueva
    0.55
    ጄ
    0.52
    നിന്ന്
    0.51
     nije
    0.50
    대전
    0.50
    āj
    0.49
     decode
    0.49
    ademie
    0.48
    ﻯ
    0.48
    accion
    0.48
    Activations Density 0.133%

    No Known Activations