© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139433
    Prev
    Next
    INDEX
    Explanations

    argument names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    <0x0D>
    0.53
    ...
    0.53
    The
    0.52
    ↵
    0.52
    ที่
    0.50
    4
    0.50
    ..\
    0.50
    ээ
    0.49
    Simulator
    0.48
     choreographer
    0.48
    POSITIVE LOGITS
    ⵙ
    0.64
     Yukawa
    0.63
    ᴺ
    0.63
     ricos
    0.56
    蒎
    0.56
    ᴹ
    0.55
    lbrakk
    0.54
     revê
    0.54
     Renewable
    0.54
    
    0.54
    Activations Density 0.010%

    No Known Activations