© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205750
    Prev
    Next
    INDEX
    Explanations

    Etsy platform

    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_6_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
     It
    1.10
    ano
    0.92
    s
    0.91
    ના
    0.90
    eti
    0.86
    uli
    0.84
    出
    0.82
    你
    0.80
    с
    0.78
    est
    0.77
    POSITIVE LOGITS
    Ⲑ
    1.05
    ;
    1.01
     tassels
    0.98
     manly
    0.97
     walkway
    0.96
     insuff
    0.96
     pectoral
    0.90
     encroach
    0.87
     strikeouts
    0.85
     fuselage
    0.84
    Activations Density 0.000%

    No Known Activations