© 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. 159243
    Prev
    Next
    INDEX
    Explanations

    SUB

    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
     sw
    0.43
    iane
    0.38
    afe
    0.38
    Sw
    0.37
    ousal
    0.37
    வீன
    0.37
     शेट्टी
    0.37
    Ị
    0.36
    restriction
    0.36
    rmann
    0.36
    POSITIVE LOGITS
     Gagn
    0.41
     किल
    0.41
    iel
    0.40
    ில்
    0.37
    ード
    0.37
     生命周期函数
    0.37
     Thiên
    0.36
    ěl
    0.36
    ारात
    0.36
    ّل
    0.36
    Activations Density 0.001%

    No Known Activations