© 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. 48425
    Prev
    Next
    INDEX
    Explanations

    await and subsequent code

    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
     alimony
    0.37
     eastbound
    0.37
     défi
    0.37
    exclude
    0.36
     interstate
    0.35
     erbjuder
    0.35
     conflicts
    0.35
    ܚ
    0.35
     southbound
    0.35
     faktor
    0.34
    POSITIVE LOGITS
    Crown
    0.38
     wings
    0.37
    Register
    0.36
     сра
    0.36
    Wings
    0.36
     мах
    0.35
     pà
    0.35
    ppable
    0.35
    rology
    0.34
    ളം
    0.34
    Activations Density 0.036%

    No Known Activations