© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158073
    Prev
    Next
    INDEX
    Explanations

    once you

    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_2_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
    س
    1.88
    ס
    1.42
    স
    1.37
     in
    1.31
     at
    1.30
    ص
    1.09
    มี
    1.02
    ش
    1.02
    对
    1.01
    د
    1.00
    POSITIVE LOGITS
    のは
    1.21
    ue
    1.15
    í
    1.13
    bran
    1.12
    ールの
    1.10
    ﻑ
    1.09
    gean
    1.08
    cedor
    1.08
    ки
    1.07
    आई
    1.07
    Activations Density 0.002%

    No Known Activations