© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28189
    Prev
    Next
    INDEX
    Explanations

    turbulence and churning

    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
    0
    0.76
     e
    0.74
     to
    0.71
    menopausal
    0.69
    Н
    0.67
     نے
    0.67
    been
    0.67
     کے
    0.66
    Ї
    0.66
    ired
    0.65
    POSITIVE LOGITS
    ام
    0.75
    ط
    0.73
    տ
    0.68
    t
    0.65
    im
    0.65
     calme
    0.65
     Turbulence
    0.64
     accueill
    0.64
     étape
    0.63
     branco
    0.63
    Activations Density 0.034%

    No Known Activations