© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 130828
    Prev
    Next
    INDEX
    Explanations

    names and actions or descriptions

    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_25_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
    птовалю
    0.34
    Selenium
    0.33
     Ablauf
    0.33
     java
    0.33
    ribut
    0.32
     HTML
    0.32
    ateria
    0.32
    г
    0.32
    펌
    0.32
    iller
    0.31
    POSITIVE LOGITS
    כו
    0.39
     smuggling
    0.36
     overlooking
    0.35
     observers
    0.34
     undetected
    0.33
     quantifying
    0.33
     dreaming
    0.33
     unu
    0.33
     lowering
    0.32
     quantification
    0.32
    Activations Density 0.000%

    No Known Activations