© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 195845
    Prev
    Next
    INDEX
    Explanations

    core concepts, principles, or features

    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_26_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
    בום
    0.38
    руд
    0.37
    ت
    0.34
    UMPS
    0.33
     ovog
    0.32
    oriale
    0.32
    excell
    0.32
     හා
    0.31
    اتھن
    0.31
    事例
    0.31
    POSITIVE LOGITS
    9
    0.40
     প্রতিক্রিয়া
    0.40
    8
    0.37
    itating
    0.35
     året
    0.35
    iteten
    0.35
     harvest
    0.34
     Salamanca
    0.34
    ined
    0.33
    gress
    0.32
    Activations Density 0.030%

    No Known Activations