© 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. 129746
    Prev
    Next
    INDEX
    Explanations

    line Design

    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
    and
    1.24
    କ
    1.13
     Αυ
    1.08
     Ве
    1.05
     extérieur
    1.00
     Εκ
    0.99
    áférés
    0.98
     και
    0.98
     Ав
    0.98
     и
    0.98
    POSITIVE LOGITS
    .
    1.20
    $
    1.09
    লিন
    0.98
    (
    0.97
    。
    0.94
     neighbourhood
    0.93
    ।
    0.92
    วิธี
    0.91
     diuretic
    0.91
    0.91
    Activations Density 0.001%

    No Known Activations