© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31515
    Prev
    Next
    INDEX
    Explanations

    JSON response keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    willReturn
    0.37
     vapeur
    0.36
    ha
    0.34
     международного
    0.33
    ｿ
    0.33
    أي
    0.32
     quaisquer
    0.32
     бясплат
    0.32
     नपु
    0.32
    化物
    0.32
    POSITIVE LOGITS
     producer
    0.36
    सद
    0.35
    ernel
    0.34
     पहल
    0.33
     measures
    0.33
    姩
    0.33
     Producer
    0.32
     mesure
    0.32
     paymentRequest
    0.32
     preguntó
    0.32
    Activations Density 0.003%

    No Known Activations