© 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. 220406
    Prev
    Next
    INDEX
    Explanations

    Students will learn

    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
     compat
    0.39
     entity
    0.38
     یا
    0.38
    Jade
    0.37
    AtIndexPath
    0.36
     &/
    0.36
    与其
    0.36
     غال
    0.36
     связана
    0.35
    ocompat
    0.35
    POSITIVE LOGITS
    ytuc
    0.42
     Weather
    0.39
     ♦
    0.39
     TIP
    0.38
     stabilizes
    0.38
     Luật
    0.38
    PI
    0.37
     Koff
    0.37
     Duration
    0.37
     USER
    0.36
    Activations Density 0.001%

    No Known Activations