© 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. 130126
    Prev
    Next
    INDEX
    Explanations

    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
    ੋਂ
    0.46
    няя
    0.41
    NESS
    0.41
    neſs
    0.41
    revista
    0.40
    תו
    0.40
    皤
    0.40
    ness
    0.40
    relief
    0.40
    ню
    0.39
    POSITIVE LOGITS
    conom
    0.57
    chanical
    0.56
     nhàng
    0.55
    lectric
    0.54
    cker
    0.52
    ́
    0.52
    mber
    0.51
    ttes
    0.50
    ază
    0.50
    eeee
    0.49
    Activations Density 0.000%

    No Known Activations