© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206652
    Prev
    Next
    INDEX
    Explanations

    shape, geometry, object, injury, base, image

    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_20_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
     makeup
    0.29
     HAY
    0.28
    外
    0.28
     ((
    0.28
     guardianship
    0.28
     sting
    0.27
    ocrates
    0.27
     craftsmanship
    0.27
    屋
    0.27
     कोई
    0.27
    POSITIVE LOGITS
    }_{
    0.33
    喎
    0.31
     тоді
    0.31
     partic
    0.31
    romatic
    0.30
    Then
    0.30
     verwendeten
    0.30
    Matic
    0.29
     भएका
    0.29
     jeweil
    0.29
    Activations Density 0.001%

    No Known Activations