© 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. 6626
    Prev
    Next
    INDEX
    Explanations

    refer

    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
     dip
    0.43
    dip
    0.38
     Griffith
    0.36
     rec
    0.35
     urs
    0.35
     tubercul
    0.35
    മിന്റെ
    0.35
    ቦ
    0.34
    право
    0.34
     Tyler
    0.33
    POSITIVE LOGITS
     مشکل
    0.40
    렙
    0.39
    ereum
    0.39
    ίνουν
    0.38
     cro
    0.37
    )(&
    0.37
    inados
    0.37
    érences
    0.36
     ILL
    0.36
     आद
    0.35
    Activations Density 0.076%

    No Known Activations