© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78760
    Prev
    Next
    INDEX
    Explanations

    cel with following suffixes like est, ery, adon, onis

    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_0_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
    (
    1.30
    ลด
    1.22
    ลอง
    1.13
     μία
    1.08
    ו
    1.07
    ש
    1.07
     χρήση
    1.03
    지
    1.02
    들이
    1.02
    inous
    1.02
    POSITIVE LOGITS
    ך
    1.81
     a
    1.70
     are
    1.59
    า
    1.58
     it
    1.52
    ır
    1.52
    كن
    1.41
     was
    1.37
    et
    1.35
    я
    1.27
    Activations Density 0.001%

    No Known Activations