© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49423
    Prev
    Next
    INDEX
    Explanations

    ASCII art and code snippets

    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
    Negative
    0.37
    Mixing
    0.37
     ru
    0.36
     Mixing
    0.36
    柜
    0.36
    行情
    0.35
    Fake
    0.34
    সাইন
    0.34
     unreliable
    0.33
     lejos
    0.33
    POSITIVE LOGITS
    reserved
    0.42
    ridden
    0.41
    ABLES
    0.38
    getResource
    0.38
    selectable
    0.37
    ˆ
    0.37
     disediakan
    0.37
    ansi
    0.36
    ƒ
    0.36
    罅
    0.36
    Activations Density 0.001%

    No Known Activations