© 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. 228123
    Prev
    Next
    INDEX
    Explanations

    tumblr api

    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
    v
    1.15
     of
    1.06
     The
    0.89
    im
    0.86
    il
    0.84
    ренности
    0.82
    UM
    0.81
    ুই
    0.81
     ३
    0.79
    த்தர
    0.79
    POSITIVE LOGITS
    ي
    1.18
    ير
    1.12
    ล
    1.09
    يع
    1.05
    ات
    1.04
    nú
    1.01
    يت
    0.98
    اتي
    0.98
    其他
    0.98
    بير
    0.95
    Activations Density 0.000%

    No Known Activations