© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2182
    Prev
    Next
    INDEX
    Explanations

    Invention, embodiments, methods, system, US

    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_39_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
    Upsilon
    0.26
    雲
    0.25
    read
    0.24
    ড়ো
    0.24
     Soccer
    0.24
    TextureData
    0.24
     sop
    0.24
    bark
    0.23
     cruel
    0.23
    ּ
    0.23
    POSITIVE LOGITS
     //@
    0.27
     되어
    0.26
    刺
    0.25
     vajj
    0.25
     textAppearance
    0.25
     নূতন
    0.25
     интегри
    0.25
    teau
    0.24
    辟
    0.24
     coaction
    0.24
    Activations Density 0.007%

    No Known Activations