© 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. 51392
    Prev
    Next
    INDEX
    Explanations

    Lets followed by verb

    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
    ین
    1.02
    ่
    0.89
    ات
    0.84
    し
    0.84
    ದ
    0.84
     бизнеса
    0.82
    ي
    0.80
     и
    0.79
    ุ
    0.79
     it
    0.77
    POSITIVE LOGITS
    h
    0.80
    ган
    0.75
    att
    0.73
    listar
    0.73
    ſh
    0.71
     Vail
    0.71
    nG
    0.71
    gages
    0.71
     بر
    0.71
     Jego
    0.71
    Activations Density 0.002%

    No Known Activations