© 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. 61519
    Prev
    Next
    INDEX
    Explanations

    kebabs

    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
     been
    1.18
     it
    1.11
    ")))
    1.09
    1
    1.02
    D
    1.02
     pertence
    0.99
     ۱
    0.96
    ۱
    0.96
     you
    0.95
    IC
    0.95
    POSITIVE LOGITS
    am
    1.46
    i
    1.40
    م
    1.29
    ا
    1.11
    ي
    1.07
    다
    1.07
    (
    1.06
    内容
    1.00
    d
    1.00
    ط
    0.96
    Activations Density 0.002%

    No Known Activations