© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21583
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_56_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
     hundred
    3.02
     Hundred
    2.73
    Hundred
    2.63
    百
    2.59
    hundred
    2.42
     hund
    2.39
     thousand
    2.30
     hundert
    2.22
     Thousand
    2.09
     百
    2.05
    POSITIVE LOGITS
    fileID
    0.37
    甫
    0.36
    etically
    0.36
     Brice
    0.34
     decode
    0.34
     intermission
    0.34
     Frost
    0.33
     frapp
    0.33
     Sebastián
    0.33
     बेर
    0.32
    Activations Density 0.083%

    No Known Activations