© 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. 111930
    Prev
    Next
    INDEX
    Explanations

    women

    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
    。
    1.01
    ле
    0.90
     are
    0.82
    ти
    0.82
     Are
    0.71
    ра
    0.70
     інші
    0.70
    ט
    0.69
    。",
    0.67
    ।,
    0.66
    POSITIVE LOGITS
     to
    1.13
    5
    0.96
    2
    0.92
    </h2>
    0.88
    AK
    0.86
    </strong>
    0.81
    </em>
    0.81
    7
    0.81
    </h3>
    0.80
    ade
    0.80
    Activations Density 0.009%

    No Known Activations