© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50528
    Prev
    Next
    INDEX
    Explanations

    login or register buttons

    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_31_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
    NCR
    0.29
     sexto
    0.29
     মিঃ
    0.28
    䣼
    0.28
    udir
    0.28
    ênd
    0.28
    𝗚
    0.28
    Products
    0.28
    جہ
    0.28
    えます
    0.28
    POSITIVE LOGITS
     presentations
    0.34
    vinyl
    0.33
     vinyl
    0.31
    enske
    0.31
    抖
    0.30
     Blackmore
    0.30
     inelastic
    0.29
     socialism
    0.29
    obranch
    0.29
     reimburse
    0.29
    Activations Density 0.002%

    No Known Activations