© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216341
    Prev
    Next
    INDEX
    Explanations

    names

    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_50_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
     Wag
    0.40
    rhein
    0.39
     Logan
    0.39
     hol
    0.39
     Ry
    0.38
     heroes
    0.38
     Ett
    0.38
    <0x0E>
    0.37
     kapp
    0.37
     Romain
    0.36
    POSITIVE LOGITS
     alveolar
    0.42
    क्सी
    0.41
    Ante
    0.41
    isPresent
    0.41
     sot
    0.40
    الصف
    0.40
    炁
    0.40
    脘
    0.40
    ARRANT
    0.39
    Lucy
    0.39
    Activations Density 0.000%

    No Known Activations