© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202105
    Prev
    Next
    INDEX
    Explanations

    assertRaises exception

    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_12_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
     зберіга
    0.47
     immunized
    0.46
     مان
    0.46
    .*/
    0.45
     renormalized
    0.45
    িয়া
    0.45
    ⃞
    0.45
    āo
    0.45
     ZO
    0.45
     conserved
    0.44
    POSITIVE LOGITS
     to
    0.49
     Ried
    0.46
    LC
    0.46
     Jodie
    0.44
     a
    0.44
    controller
    0.44
    чение
    0.43
     Determination
    0.43
     Cie
    0.43
     Thompson
    0.43
    Activations Density 0.000%

    No Known Activations