© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204940
    Prev
    Next
    INDEX
    Explanations

    his or her

    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
     an
    1.21
     a
    1.09
    et
    1.02
     as
    1.00
     ك
    0.98
     mezcla
    0.98
    ك
    0.98
    }_
    0.93
     =
    0.93
    к
    0.93
    POSITIVE LOGITS
    at
    1.06
    ات
    1.02
    atka
    0.98
    יים
    0.95
    ્સ
    0.95
    يها
    0.94
    ↵↵
    0.93
    يا
    0.93
    .
    0.92
    ınız
    0.91
    Activations Density 0.001%

    No Known Activations