© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31120
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     الص
    0.43
    钡
    0.41
    ionized
    0.41
    ితే
    0.40
    ೬
    0.40
     anion
    0.40
     Emily
    0.39
     Topology
    0.38
     isolate
    0.37
    喤
    0.37
    POSITIVE LOGITS
    Lea
    0.69
     Lea
    0.67
    LEA
    0.54
    Len
    0.50
     Len
    0.44
     lea
    0.44
    Grand
    0.43
    Shaw
    0.43
    Blue
    0.43
     Grand
    0.43
    Activations Density 0.000%

    No Known Activations