© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155619
    Prev
    Next
    INDEX
    Explanations

    f or Fe

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     व्याप्त
    0.39
     измене
    0.38
    磨
    0.38
    kern
    0.37
     percepción
    0.37
     întâ
    0.37
     tomando
    0.37
     entitlements
    0.36
     Hin
    0.36
    evoluzione
    0.36
    POSITIVE LOGITS
    Ｖ
    0.43
    isted
    0.40
     Harmon
    0.40
    V
    0.40
     cohes
    0.39
    ┐
    0.38
     markings
    0.38
    OUGH
    0.37
    v
    0.37
     cohesive
    0.37
    Activations Density 0.002%

    No Known Activations