© 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. 166930
    Prev
    Next
    INDEX
    Explanations

    but followed by contrast

    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
     Turned
    0.32
    dragging
    0.31
    stered
    0.29
     beforeEach
    0.29
    TURN
    0.28
     Handwriting
    0.28
    Mayo
    0.27
    ↥
    0.27
    ровку
    0.27
     inversiones
    0.27
    POSITIVE LOGITS
    érc
    0.30
    icrobial
    0.30
    ãi
    0.29
     än
    0.29
     native
    0.28
     manu
    0.28
    ligen
    0.28
     includ
    0.27
     ailing
    0.27
     rejuvenated
    0.27
    Activations Density 0.020%

    No Known Activations