© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45286
    Prev
    Next
    INDEX
    Explanations

    programming type declarations

    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_22_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
     ors
    0.46
    millis
    0.41
     calcite
    0.41
     hidro
    0.40
    钙
    0.39
    ibol
    0.38
     Hydro
    0.38
     वजह
    0.37
    tois
    0.37
     ಪಡೆ
    0.37
    POSITIVE LOGITS
     என்னுடைய
    0.44
    ễn
    0.42
    につき
    0.41
    如图
    0.40
     đừng
    0.39
     situate
    0.39
    爫
    0.38
     부탁
    0.38
    кать
    0.37
    rezent
    0.37
    Activations Density 0.005%

    No Known Activations