© 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. 148773
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     sensation
    0.37
     例如
    0.36
     metade
    0.36
     contrats
    0.35
     recollection
    0.35
     आपली
    0.35
     __________
    0.35
     ол
    0.34
     route
    0.34
     flusso
    0.34
    POSITIVE LOGITS
     per
    0.63
    per
    0.47
    千
    0.40
     प्रति
    0.40
    ിലും
    0.39
    PerRow
    0.37
    跟你
    0.37
    𝗟
    0.37
    this
    0.36
    Per
    0.36
    Activations Density 0.000%

    No Known Activations