© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13264
    Prev
    Next
    INDEX
    Explanations

    virtuous, industrious

    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
     sion
    0.49
     än
    0.47
     [
    0.47
     himself
    0.46
    彼は
    0.46
     alm
    0.46
     दुस
    0.46
    </strong>
    0.45
    न्होंने
    0.45
     abon
    0.45
    POSITIVE LOGITS
    JSX
    0.51
    hx
    0.49
    cool
    0.49
    yarn
    0.49
    Ele
    0.48
    kh
    0.47
    jsx
    0.47
    aldehyde
    0.47
    punctuation
    0.46
     okre
    0.45
    Activations Density 0.000%

    No Known Activations