© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161753
    Prev
    Next
    INDEX
    Explanations

    Oort Cloud

    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_2_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
    4
    1.54
    ان
    1.33
    an
    1.25
    ad
    1.24
    ت
    1.23
    6
    1.21
    0
    1.19
    ك
    1.16
    ق
    1.15
    ät
    1.13
    POSITIVE LOGITS
    רי
    1.15
    い
    1.14
    。</
    1.03
     aument
    1.02
    '.$
    1.02
     to
    1.02
    ﺍ
    1.01
     TYPE
    0.97
    ामुळे
    0.96
     CARD
    0.95
    Activations Density 0.000%

    No Known Activations