© 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. 5250
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands

    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
     lust
    0.41
     বিভক্ত
    0.38
     അന
    0.38
    SqlConnection
    0.38
     scenic
    0.37
     Tas
    0.36
    萺
    0.36
    σιο
    0.35
     Arct
    0.35
     Arch
    0.35
    POSITIVE LOGITS
     hor
    0.38
     rif
    0.38
     timp
    0.36
    ixir
    0.36
     င
    0.36
     सिंगर
    0.36
    igts
    0.36
     Kimball
    0.36
     algod
    0.36
     exp
    0.35
    Activations Density 0.001%

    No Known Activations