© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5907
    Prev
    Next
    INDEX
    Explanations

    (x, positions

    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_39_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
     Greer
    0.42
     खोसला
    0.38
     DNIs
    0.37
    ურთიერთ
    0.36
     chromospheres
    0.36
     Dupree
    0.36
    秕
    0.35
     utilitarian
    0.35
     الدهون
    0.35
     کریں
    0.35
    POSITIVE LOGITS
    alpha
    0.38
    p
    0.36
    μ
    0.33
     p
    0.33
     u
    0.32
    sigma
    0.32
    ECS
    0.32
    α
    0.32
     α
    0.31
    S
    0.31
    Activations Density 0.097%

    No Known Activations