© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    4. 99629
    Prev
    Next
    INDEX
    Explanations

    concepts related to data and analysis

    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_16_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
    Ess
    0.47
    Upgrade
    0.46
    트
    0.46
    Undo
    0.46
    ล
    0.45
    𝓽
    0.45
    ین
    0.45
    ⌟
    0.45
    可能な
    0.45
    מס
    0.45
    POSITIVE LOGITS
     greeted
    0.58
     sentimental
    0.49
     doctora
    0.49
     liter
    0.49
     agreg
    0.49
     cH
    0.48
     beantwort
    0.48
    ْنَ
    0.47
     met
    0.46
     prensa
    0.46
    Activations Density 0.000%

    No Known Activations