© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214989
    Prev
    Next
    INDEX
    Explanations

    code linting

    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_5_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
    s
    1.38
    h
    1.36
    í
    1.30
    ні
    1.21
    \
    1.13
    m
    1.11
    I
    1.07
    ll
    1.05
    na
    1.05
    0
    1.05
    POSITIVE LOGITS
     on
    1.59
    ↵
    1.17
    る
    1.05
    고
    1.02
    त
    0.91
     карти
    0.89
     khả
    0.89
    чал
    0.88
    かで
    0.88
     сете
    0.87
    Activations Density 0.001%

    No Known Activations