© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199142
    Prev
    Next
    INDEX
    Explanations

    basis points or percentages

    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_27_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
    Ⴚ
    0.44
    琴
    0.39
    цыя
    0.38
     loosing
    0.37
    <unused57>
    0.36
     destroying
    0.36
     попы
    0.36
     ciem
    0.36
     Oberfläche
    0.35
     ଭ
    0.34
    POSITIVE LOGITS
     percentages
    0.44
    filed
    0.40
    ত্ত
    0.40
    percent
    0.38
    Filed
    0.38
     फीसद
    0.38
     percent
    0.38
     फीसदी
    0.37
     प्रतिशत
    0.37
     filed
    0.36
    Activations Density 0.000%

    No Known Activations