© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8468
    Prev
    Next
    INDEX
    Explanations

    end of phrase markers

    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_40_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
     başladı
    0.44
     başlad
    0.41
     DELIVERY
    0.41
     தடு
    0.40
     Hagan
    0.39
     começou
    0.38
     comenzamos
    0.38
    怏
    0.38
    VERTISING
    0.38
    ãos
    0.37
    POSITIVE LOGITS
     behind
    0.44
    quire
    0.44
    前面
    0.44
     '
    0.42
    chil
    0.42
     Behind
    0.41
    Behind
    0.41
     sheet
    0.41
    Ku
    0.39
     reuni
    0.39
    Activations Density 0.001%

    No Known Activations