© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 60720
    Prev
    Next
    INDEX
    Explanations

    :**

    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_59_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
     http
    0.49
     ../
    0.45
    podcast
    0.41
    homework
    0.41
    http
    0.41
    workout
    0.41
     」,
    0.41
    abs
    0.40
    exams
    0.40
     \%$.
    0.40
    POSITIVE LOGITS
    --
    0.54
     Among
    0.52
     They
    0.49
    </h1>
    0.48
    While
    0.47
     While
    0.46
    Among
    0.46
     Some
    0.45
     Those
    0.45
     Because
    0.44
    Activations Density 0.020%

    No Known Activations