© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102265
    Prev
    Next
    INDEX
    Explanations

    pair

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    ᱩ
    0.41
    stool
    0.38
    rf
    0.38
     LANA
    0.37
     LES
    0.37
    utter
    0.37
    enciones
    0.36
     DISC
    0.36
    THON
    0.36
     colloidal
    0.36
    POSITIVE LOGITS
    ไข
    0.39
    AttrName
    0.38
    Elems
    0.37
     Ga
    0.36
    rát
    0.36
    Ẻ
    0.36
    гноз
    0.35
    хим
    0.35
    ņi
    0.34
    招标文件
    0.34
    Activations Density 0.002%

    No Known Activations