© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 144
    Prev
    Next
    INDEX
    Explanations

    openai.com blog, policies, pricing

    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_40_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
     النص
    0.37
     unspo
    0.33
    Arist
    0.32
     রাম
    0.31
     Hunan
    0.31
    均
    0.31
    しゃ
    0.30
    牯
    0.30
     Carpet
    0.30
    ITHER
    0.30
    POSITIVE LOGITS
     Integration
    0.39
    Integration
    0.39
    ByKey
    0.38
     آہ
    0.37
     registre
    0.36
     रजिस्ट्री
    0.36
    request
    0.35
     Ire
    0.35
     Bola
    0.35
     розпо
    0.34
    Activations Density 0.015%

    No Known Activations