© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46369
    Prev
    Next
    INDEX
    Explanations

    " v , EC, house

    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_13_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
     Dots
    0.50
    \$
    0.49
    {
    0.47
     besch
    0.47
     Stre
    0.44
     находиться
    0.42
     Dos
    0.42
     benefactor
    0.42
    </code>
    0.41
     stre
    0.41
    POSITIVE LOGITS
    𝕌
    0.57
    𝕦
    0.56
     izinsuku
    0.51
    Zhou
    0.50
    TextInput
    0.49
    owskiego
    0.49
     لوی
    0.49
    plectic
    0.49
    ್ಯಾ
    0.48
    りたい
    0.48
    Activations Density 0.000%

    No Known Activations