© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156848
    Prev
    Next
    INDEX
    Explanations

    số, điểm, gợi ý, ví dụ

    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_2_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
    0.69
    d
    0.68
    .
    0.68
    S
    0.66
    -
    0.63
    dogs
    0.62
    c
    0.61
    rill
    0.60
    2
    0.60
    dioxide
    0.59
    POSITIVE LOGITS
    ین
    0.76
    т
    0.76
    ні
    0.73
    ில்
    0.71
    ة
    0.68
    ర్
    0.64
    ро
    0.63
    ного
    0.63
    ə
    0.63
    м
    0.62
    Activations Density 0.000%

    No Known Activations