© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120020
    Prev
    Next
    INDEX
    Explanations

    public class

    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_27_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
    consin
    0.41
    utie
    0.40
    անակ
    0.40
    )/(
    0.39
     جهت
    0.39
    édération
    0.39
     Hän
    0.39
    肩膀
    0.39
    seyside
    0.38
    kowej
    0.38
    POSITIVE LOGITS
     ສະ
    0.45
    浅
    0.41
     fazendo
    0.41
     Searches
    0.40
     índices
    0.40
    Search
    0.40
     asing
    0.40
     Search
    0.39
    وروب
    0.39
     Mortality
    0.39
    Activations Density 0.001%

    No Known Activations