© 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. 79842
    Prev
    Next
    INDEX
    Explanations

    3Blue1Brown math explanations

    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
     pedest
    0.30
    times
    0.29
    மதி
    0.29
     मझ
    0.29
     Mountains
    0.29
    씩
    0.29
     Poster
    0.28
    spender
    0.28
    Seasonal
    0.28
    িজ
    0.28
    POSITIVE LOGITS
    斋
    0.40
     Noz
    0.37
     conspiracies
    0.37
    Zam
    0.36
     Libro
    0.36
    ச்சார
    0.35
     ploy
    0.35
     piping
    0.35
     Kleid
    0.35
    çons
    0.35
    Activations Density 0.002%

    No Known Activations