© 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. 32069
    Prev
    Next
    INDEX
    Explanations

    github

    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
     PCIe
    0.41
     ($
    0.40
    Vide
    0.39
    uable
    0.38
    House
    0.38
     XII
    0.38
    dzi
    0.37
    luk
    0.36
     dlg
    0.36
    ස්
    0.36
    POSITIVE LOGITS
    fh
    0.41
    FB
    0.40
    aları
    0.40
     FB
    0.40
     الري
    0.40
     ana
    0.38
    侧
    0.38
    Chats
    0.38
     CMT
    0.38
    fts
    0.37
    Activations Density 0.000%

    No Known Activations