© 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. 79681
    Prev
    Next
    INDEX
    Explanations

    explaining or focusing

    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_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
    方面的
    0.40
    㑬
    0.40
     সংক্রান্ত
    0.39
    度の
    0.38
     관련된
    0.38
     संबंधी
    0.38
    逺
    0.37
    ့
    0.37
    仼
    0.37
     مذہب
    0.37
    POSITIVE LOGITS
     Knot
    0.40
     Highlight
    0.38
     Final
    0.36
     Leder
    0.36
     Ceci
    0.36
    Handler
    0.34
     (**
    0.34
     Katzen
    0.34
     Эта
    0.34
    requires
    0.34
    Activations Density 0.010%

    No Known Activations