© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60213
    Prev
    Next
    INDEX
    Explanations

    ordering by likelihood

    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
    ↵
    1.38
    ੇ
    0.93
    </h3>
    0.91
    ung
    0.87
    け
    0.85
    </h6>
    0.82
    ل
    0.81
    ル
    0.79
    </h2>
    0.78
    </h4>
    0.77
    POSITIVE LOGITS
    s
    1.68
     in
    1.45
    o
    1.24
    y
    1.24
    는
    1.21
    e
    1.19
    是真的
    1.10
    ۔
    1.08
    a
    1.04
    是
    1.04
    Activations Density 0.001%

    No Known Activations