© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231349
    Prev
    Next
    INDEX
    Explanations

    storage drive

    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_6_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
    지
    1.16
    ่า
    1.12
    ق
    1.12
    as
    0.93
     inhalation
    0.93
    it
    0.92
    त्र
    0.92
    زان
    0.89
    る
    0.89
    ма
    0.88
    POSITIVE LOGITS
    j
    1.08
    jší
    1.02
    ni
    0.99
    ක්
    0.98
    ৫
    0.98
     опа
    0.96
    N
    0.95
     TouchUtils
    0.94
    cknowled
    0.93
    TI
    0.93
    Activations Density 0.002%

    No Known Activations