© 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. 53049
    Prev
    Next
    INDEX
    Explanations

    angel and angels

    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
     കിട
    0.38
     influential
    0.38
    openweathermap
    0.38
    叄
    0.38
     叶
    0.37
    باز
    0.36
    STRUCTION
    0.36
    cau
    0.36
     باش
    0.35
    Idents
    0.35
    POSITIVE LOGITS
     пас
    0.40
    ㅢ
    0.40
     gravity
    0.38
    vehicles
    0.37
     sg
    0.37
     outfits
    0.36
    etok
    0.36
     Pas
    0.35
     broad
    0.35
     هزینه
    0.35
    Activations Density 0.000%

    No Known Activations