© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54353
    Prev
    Next
    INDEX
    Explanations

    2023 and 2024

    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_30_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
     wrought
    0.28
     графи
    0.28
     Воло
    0.28
     ಗ್ರಾ
    0.27
     extraordinary
    0.27
    提
    0.27
     Selling
    0.27
     extraordin
    0.26
    ,|
    0.25
     Graphical
    0.25
    POSITIVE LOGITS
    next
    0.33
    iciency
    0.32
    ensione
    0.31
    annual
    0.29
     Baseline
    0.29
    season
    0.29
    episode
    0.28
    Annual
    0.28
    incidence
    0.28
    ometraje
    0.27
    Activations Density 0.004%

    No Known Activations