© 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. 35937
    Prev
    Next
    INDEX
    Explanations

    ber/be/bean

    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
    leben
    0.45
    wind
    0.42
    cen
    0.42
    セット
    0.41
     set
    0.41
     Set
    0.41
     Exponential
    0.40
    絓
    0.40
    wild
    0.40
    nown
    0.40
    POSITIVE LOGITS
    ccos
    0.43
     proteomics
    0.39
    ルコ
    0.38
    럭
    0.37
    гел
    0.37
    સાર
    0.37
    ცა
    0.36
     Marlow
    0.35
     remotely
    0.34
    TextStyle
    0.34
    Activations Density 0.005%

    No Known Activations