© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62578
    Prev
    Next
    INDEX
    Explanations

    five

    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
     १६
    0.50
    !»
    0.46
    »;
    0.46
    २
    0.46
    ❗️
    0.46
     Sixteen
    0.44
    ២
    0.44
    }\|
    0.43
     ២
    0.43
    ⁶
    0.43
    POSITIVE LOGITS
     five
    0.49
    0.43
    Five
    0.41
     خمسه
    0.40
    five
    0.40
    '){
    0.39
    五
    0.38
     пяти
    0.38
    ]){
    0.37
     cinq
    0.37
    Activations Density 0.001%

    No Known Activations