© 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. 60624
    Prev
    Next
    INDEX
    Explanations

    links and code

    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
     Needed
    0.46
     .
    0.46
    Unavailable
    0.46
     Not
    0.46
     Unavailable
    0.46
     Validity
    0.45
    Invalid
    0.45
    [\
    0.44
     नॉट
    0.44
    .
    0.44
    POSITIVE LOGITS
     N
    0.57
     under
    0.46
     sotto
    0.46
     под
    0.43
     Haven
    0.42
     aun
    0.41
     Guerre
    0.40
    ikten
    0.40
    ritto
    0.40
    ეტ
    0.39
    Activations Density 0.006%

    No Known Activations