© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46708
    Prev
    Next
    INDEX
    Explanations

    air thick with

    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_10_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
    وم
    0.79
    :$
    0.73
    S
    0.72
    주
    0.68
     are
    0.67
     exagger
    0.67
     protrusions
    0.67
     substrates
    0.66
    ,
    0.65
     orthogon
    0.64
    POSITIVE LOGITS
     ပြော
    0.71
    webElement
    0.67
    textColour
    0.67
    setLocation
    0.64
    att
    0.63
     જન્મદિવસ
    0.61
    azioni
    0.61
    ício
    0.61
     वेळ
    0.60
     सौरभ
    0.59
    Activations Density 0.013%

    No Known Activations