© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230449
    Prev
    Next
    INDEX
    Explanations

    crude oil

    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
    á
    1.27
    اً
    1.23
    í
    1.16
    ні
    0.99
    ا
    0.97
    िक
    0.97
    اں
    0.96
    ა
    0.96
    ди
    0.95
    منا
    0.95
    POSITIVE LOGITS
     ו
    1.00
     ﺍ
    0.99
     Ա
    0.98
     großer
    0.96
     എന്റെ
    0.95
     });
    0.92
    ra
    0.90
     besar
    0.90
     അദ്ദേഹം
    0.90
     großen
    0.89
    Activations Density 0.000%

    No Known Activations