© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 9922
    Prev
    Next
    INDEX
    Explanations

    favicon and icons

    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
     ად
    0.42
    霭
    0.38
    死去
    0.38
    ⛷
    0.38
     ऑड
    0.37
    的女
    0.37
    सायटी
    0.37
     अफसर
    0.37
     آخر
    0.36
     enanti
    0.36
    POSITIVE LOGITS
    Apple
    0.39
     Apple
    0.37
    ios
    0.37
    Γ
    0.36
     Apples
    0.36
     Portugal
    0.36
    SCC
    0.35
     Ronaldo
    0.35
    apple
    0.35
    cccc
    0.35
    Activations Density 0.002%

    No Known Activations