© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25023
    Prev
    Next
    INDEX
    Explanations

    east of Ukraine, Spain, England, South of Spain

    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_10_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
    ↵
    0.85
    ă
    0.70
    '
    0.66
    ？
    0.60
    UK
    0.60
    oppers
    0.59
    </b>
    0.57
     as
    0.57
    iors
    0.56
    阴
    0.56
    POSITIVE LOGITS
     كثير
    0.71
     שלו
    0.64
    紶
    0.59
     fileCopy
    0.58
     photospheric
    0.58
    மது
    0.57
     sinnv
    0.57
    噢
    0.56
     Convolution
    0.55
    icher
    0.55
    Activations Density 0.024%

    No Known Activations