© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212340
    Prev
    Next
    INDEX
    Explanations

    head

    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_43_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
    км
    0.40
    edk
    0.38
     densidad
    0.38
    କ
    0.38
     রহমান
    0.37
     crook
    0.37
    Pul
    0.37
    megapixel
    0.37
     oxyd
    0.37
     Sousa
    0.37
    POSITIVE LOGITS
     Head
    0.51
    Head
    0.50
     head
    0.47
    頭
    0.41
     رأس
    0.40
    䉿
    0.39
     মাথ
    0.39
    𝙽
    0.39
     baş
    0.38
    䫒
    0.38
    Activations Density 0.001%

    No Known Activations