© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16771
    Prev
    Next
    INDEX
    Explanations

    want / interest

    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_40_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
    镊
    0.38
    pture
    0.35
    ную
    0.34
    লাস
    0.34
    ricted
    0.33
    áne
    0.33
    тров
    0.32
    岂
    0.32
    ர்த
    0.32
     чем
    0.32
    POSITIVE LOGITS
     interest
    2.81
     Interest
    2.55
    interest
    2.50
    Interest
    2.42
     interested
    2.39
     interes
    2.39
     interess
    2.39
     interesse
    2.38
     interés
    2.34
     Interesse
    2.30
    Activations Density 0.240%

    No Known Activations