© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53129
    Prev
    Next
    INDEX
    Explanations

    math notation

    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_55_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
     {(
    0.40
    '',
    0.39
    Rc
    0.39
     brush
    0.38
     anges
    0.37
     {,
    0.37
     sulfite
    0.36
    ävä
    0.36
    FIN
    0.36
    rü
    0.36
    POSITIVE LOGITS
    ាក
    0.39
     }}=
    0.38
    🦗
    0.37
     $:
    0.37
    него
    0.37
    щего
    0.37
    🎶
    0.36
    มาณ
    0.36
     ঃ
    0.35
    шого
    0.35
    Activations Density 0.008%

    No Known Activations