© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169726
    Prev
    Next
    INDEX
    Explanations

    India

    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_56_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
     HAVING
    0.51
    -‘
    0.43
     having
    0.42
    -.
    0.42
     typically
    0.39
    abez
    0.39
    -"
    0.38
     والج
    0.38
    '-
    0.38
    -'
    0.38
    POSITIVE LOGITS
     Rs
    0.52
     Bhai
    0.48
    Delhi
    0.48
     salwar
    0.46
     Diwali
    0.44
     Delhi
    0.43
     Hyderabad
    0.43
     rupees
    0.43
     saree
    0.43
     Manohar
    0.42
    Activations Density 0.002%

    No Known Activations