© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48991
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     ettha
    0.38
     attho
    0.36
     படத்தை
    0.35
    沪
    0.35
     Almost
    0.35
     Rope
    0.35
     glace
    0.34
     antire
    0.34
    бята
    0.33
     `>=`,
    0.33
    POSITIVE LOGITS
    󠁮
    0.38
     converges
    0.36
    τιο
    0.36
     والن
    0.35
     имеет
    0.35
     sowohl
    0.34
     отличается
    0.34
    যেমন
    0.33
    陷
    0.33
    elementReference
    0.33
    Activations Density 0.000%

    No Known Activations