© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28361
    Prev
    Next
    INDEX
    Explanations

    strikes and protests

    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_40_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
     snaps
    0.46
    หัว
    0.42
     snapping
    0.42
     Pollard
    0.42
    ধ্বনি
    0.40
    
    0.37
     అధ
    0.37
     psal
    0.37
     Oui
    0.36
     흰
    0.36
    POSITIVE LOGITS
     матрицы
    0.45
     matrix
    0.38
     matrice
    0.38
    挠
    0.37
    رويج
    0.36
     matrices
    0.36
     Midwest
    0.36
     literally
    0.35
     abgesch
    0.35
     Matrices
    0.35
    Activations Density 0.009%

    No Known Activations