© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194269
    Prev
    Next
    INDEX
    Explanations

    mention other than what's specified

    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_4_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
    的网络
    0.64
    )\
    0.55
    の外
    0.52
    的存在
    0.52
    يد
    0.52
    መሳሳይ
    0.51
    のことを
    0.51
    )
    0.51
     Grâce
    0.50
    ”
    0.50
    POSITIVE LOGITS
    т
    0.77
    ت
    0.72
    м
    0.69
    م
    0.68
    ק
    0.66
    чал
    0.65
    ان
    0.64
    AN
    0.64
    DE
    0.62
    ILL
    0.61
    Activations Density 0.000%

    No Known Activations