© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45735
    Prev
    Next
    INDEX
    Explanations

    dimensions and sizes

    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_22_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
     {\
    0.48
     \\\
    0.48
     polvo
    0.47
     {}\
    0.47
     \
    0.47
     sinistra
    0.44
     direcciones
    0.43
     jah
    0.43
     ಅಗ
    0.42
     경로
    0.42
    POSITIVE LOGITS
    较大
    0.44
    ଂ
    0.42
    Ra
    0.40
    菽
    0.39
     steadily
    0.39
    plementation
    0.38
    вался
    0.37
    差距
    0.37
     அம்பேத்க
    0.37
    <unused100>
    0.37
    Activations Density 0.001%

    No Known Activations