© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29825
    Prev
    Next
    INDEX
    Explanations

    `DEFAULT` or `NULL` with `COMMENT`

    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_40_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
     प्रश्‍न
    0.35
    eries
    0.35
     Hole
    0.35
     систе
    0.35
     Archived
    0.34
     चूक
    0.34
    번
    0.34
     reple
    0.34
     이동
    0.33
     klad
    0.33
    POSITIVE LOGITS
    ডেম
    0.34
     marge
    0.34
    Rm
    0.34
    Lun
    0.32
     enam
    0.31
    …</
    0.31
    rectionType
    0.31
     poppies
    0.31
     MAH
    0.31
    Fus
    0.31
    Activations Density 0.001%

    No Known Activations