© 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. 216203
    Prev
    Next
    INDEX
    Explanations

    function

    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
    😩
    0.27
    Consulta
    0.26
    ❰
    0.26
    earic
    0.25
     खरीदें
    0.25
     laden
    0.25
    Recipe
    0.24
     extensive
    0.24
    Producer
    0.24
    க்கான
    0.24
    POSITIVE LOGITS
     Xiao
    0.32
     aper
    0.29
    trad
    0.29
    miques
    0.28
    heem
    0.28
    ⵣ
    0.28
     xWidth
    0.28
     ArrayRef
    0.27
    મને
    0.27
     preoccup
    0.27
    Activations Density 0.012%

    No Known Activations