© 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. 130203
    Prev
    Next
    INDEX
    Explanations

    football game, big game hunting

    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
    ។
    0.91
    ”。
    0.87
     THAT
    0.86
    。
    0.86
    "।
    0.83
     Están
    0.82
     that
    0.81
    "。
    0.81
     petición
    0.80
    。【
    0.80
    POSITIVE LOGITS
    ರುವ
    1.00
    ado
    0.99
    した
    0.95
    cji
    0.92
    ized
    0.89
    력
    0.88
    \})
    0.87
    ères
    0.86
    取り付け
    0.84
    쓰
    0.84
    Activations Density 0.000%

    No Known Activations