© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76359
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

    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_31_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
    ும்போது
    0.30
    উত্তরঃ
    0.30
    ➁
    0.30
    mozilla
    0.29
    Экс
    0.29
     넘어
    0.28
    чів
    0.28
    慢性
    0.28
     statutes
    0.28
    Cri
    0.28
    POSITIVE LOGITS
     सहकारी
    0.32
    ភ
    0.32
     Harp
    0.31
     f
    0.31
     Th
    0.30
     Custom
    0.30
     custom
    0.30
     Pary
    0.30
     har
    0.29
     "*
    0.29
    Activations Density 0.006%

    No Known Activations