© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38567
    Prev
    Next
    INDEX
    Explanations

    nguyen

    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_3_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
    ك
    1.16
    سي
    0.75
    স
    0.70
    ق
    0.66
    კ
    0.65
    يز
    0.64
    فك
    0.61
    في
    0.60
    ký
    0.59
    اع
    0.59
    POSITIVE LOGITS
     stessa
    0.66
     konsumen
    0.64
     theft
    0.60
    an
    0.60
    ä
    0.58
     finestra
    0.57
     dimensioni
    0.57
     membutuhkan
    0.57
    ِی
    0.56
    IOT
    0.56
    Activations Density 0.004%

    No Known Activations