© 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. 206356
    Prev
    Next
    INDEX
    Explanations

    information you

    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
    ූප
    0.46
     hücre
    0.44
     مۇ
    0.44
    荥
    0.43
     disbursed
    0.42
    亰
    0.41
    ﮢ
    0.41
     அட
    0.41
     سە
    0.41
     Cytol
    0.41
    POSITIVE LOGITS
     alterations
    0.44
     final
    0.42
     obstacle
    0.41
     other
    0.41
     Guardians
    0.41
     IOC
    0.41
     modifications
    0.40
     Operations
    0.40
     Bott
    0.40
     Controllers
    0.39
    Activations Density 0.011%

    No Known Activations