© 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. 232625
    Prev
    Next
    INDEX
    Explanations

    kevyn aucoin

    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
    ö
    1.18
    も含
    1.07
    মেন্ট
    1.00
    も
    0.99
    ও
    0.98
    。"
    0.96
    umably
    0.96
    ir
    0.93
     dolayı
    0.91
     பொதுவாக
    0.90
    POSITIVE LOGITS
     to
    1.32
    ش
    1.28
    ల
    1.18
     for
    1.16
    ж
    1.08
    s
    1.00
     as
    0.99
    자
    0.99
    기
    0.98
    ים
    0.98
    Activations Density 0.001%

    No Known Activations