© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17313
    Prev
    Next
    INDEX
    Explanations

    implements MonoBehaviour

    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
    坡
    0.40
    delegate
    0.37
    Doesn
    0.34
    parquet
    0.33
    wrapped
    0.33
    deleg
    0.33
    bral
    0.32
    startX
    0.32
    sli
    0.31
    Deleg
    0.31
    POSITIVE LOGITS
     Arrangements
    0.34
    槤
    0.34
     ordin
    0.32
    Foreground
    0.32
    आरओ
    0.32
     Routine
    0.32
    క్కి
    0.32
     Also
    0.32
     الق
    0.31
     Historic
    0.31
    Activations Density 0.001%

    No Known Activations