© 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. 174967
    Prev
    Next
    INDEX
    Explanations

    with ingredient

    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
     entusiasmo
    0.22
    及ひ
    0.22
     તથા
    0.21
     සහ
    0.21
     কাদ
    0.21
    <unused541>
    0.21
     සිදු
    0.20
     \&
    0.20
     mohabbat
    0.20
     participation
    0.20
    POSITIVE LOGITS
    the
    0.23
    Al
    0.23
    Autor
    0.22
    Remove
    0.22
    Comp
    0.21
    apol
    0.21
    rewrite
    0.21
    ιος
    0.21
    testimonial
    0.21
    linie
    0.21
    Activations Density 0.006%

    No Known Activations