© 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. 131002
    Prev
    Next
    INDEX
    Explanations

    old delta version

    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
    chmod
    0.27
     ।।
    0.27
    [][]
    0.26
            
    0.25
    oren
    0.25
    FED
    0.25
    Purch
    0.25
     উপ
    0.25
    ader
    0.25
    img
    0.24
    POSITIVE LOGITS
    ेशर
    0.27
     gps
    0.27
     Payload
    0.26
     htons
    0.25
    霊
    0.25
    アイコン
    0.25
     shipped
    0.24
     रिक्वेस्ट
    0.24
     आपल्याला
    0.24
    รี
    0.24
    Activations Density 0.001%

    No Known Activations