© 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
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206167
    Prev
    Next
    INDEX
    Explanations

    sharing, sending, hosting

    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
    上が
    0.41
    لام
    0.41
    Stanford
    0.40
    仕方
    0.40
    СО
    0.39
    واقع
    0.39
    鿆
    0.39
    വരെ
    0.38
    セプト
    0.38
    図書館
    0.38
    POSITIVE LOGITS
     onde
    0.36
     oversized
    0.35
     Trustee
    0.35
     Exception
    0.35
    tn
    0.34
     THAN
    0.34
     cadenas
    0.34
     Trust
    0.34
     tê
    0.34
    >().
    0.34
    Activations Density 0.000%

    No Known Activations