© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198620
    Prev
    Next
    INDEX
    Explanations

    edit

    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
    ningen
    0.42
    liness
    0.38
     Nu
    0.38
    anyakan
    0.37
     decks
    0.37
    謠
    0.36
    凪
    0.36
    Nu
    0.36
     berp
    0.36
    MACl
    0.36
    POSITIVE LOGITS
    Ed
    0.71
     liberation
    0.69
     ED
    0.69
     ed
    0.67
     Liberation
    0.67
     Ed
    0.67
     Эд
    0.65
    Edit
    0.64
     ईडी
    0.64
     Edit
    0.63
    Activations Density 0.000%

    No Known Activations