© 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. 171367
    Prev
    Next
    INDEX
    Explanations

    use in trademarks and commerce

    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
    ដែលអាច
    0.38
    دت
    0.37
     flot
    0.36
     yad
    0.36
     kolom
    0.36
     võivad
    0.36
     utilis
    0.35
    ;//
    0.35
     ফিল
    0.35
     bril
    0.35
    POSITIVE LOGITS
    PreviewSize
    0.40
    Close
    0.38
    тно
    0.38
    ZrO
    0.37
     izra
    0.37
     возраст
    0.36
    rentices
    0.36
    řeb
    0.36
     Enterprises
    0.36
    Wrapping
    0.36
    Activations Density 0.001%

    No Known Activations