© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61114
    Prev
    Next
    INDEX
    Explanations

    Shanghai, China and Shanghai Tower

    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_2_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
    с
    1.52
     are
    1.27
     in
    1.22
    ö
    1.00
    的有
    0.94
    ø
    0.93
     mutta
    0.91
    、
    0.90
    ामध्ये
    0.89
     এরই
    0.89
    POSITIVE LOGITS
    is
    2.59
    ت
    1.81
    y
    1.72
    the
    1.64
    n
    1.61
    t
    1.55
    י
    1.55
    ম
    1.48
    in
    1.47
    ni
    1.46
    Activations Density 0.001%

    No Known Activations