© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228302
    Prev
    Next
    INDEX
    Explanations

    start of code block

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     $\#
    0.41
     #${
    0.40
     వైసీపీ
    0.39
    INGS
    0.39
    \#
    0.39
     ইয়
    0.38
     \#
    0.38
    uddho
    0.38
     بل
    0.37
    SUV
    0.37
    POSITIVE LOGITS
     virgin
    0.44
     disen
    0.39
     chơi
    0.38
     
    0.38
     bày
    0.37
     ore
    0.37
     erlä
    0.37
    ':
    0.36
     exam
    0.36
     prez
    0.35
    Activations Density 0.001%

    No Known Activations