© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206311
    Prev
    Next
    INDEX
    Explanations

    Markdown link closing bracket followed by URL

    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_20_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
    fie
    0.63
    va
    0.57
    ita
    0.55
    ie
    0.55
    z
    0.53
    ive
    0.53
    rone
    0.52
    eine
    0.52
    emit
    0.51
    wanie
    0.51
    POSITIVE LOGITS
     prolongation
    0.49
     ofstream
    0.46
     উপস্থিত
    0.45
     elucidation
    0.44
    رین
    0.44
     resorption
    0.44
    朳
    0.44
     attham
    0.44
    𝐩
    0.43
     नु
    0.43
    Activations Density 0.001%

    No Known Activations