© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66511
    Prev
    Next
    INDEX
    Explanations

    start

    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_51_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
    kih
    0.42
    噻
    0.41
    uploads
    0.41
    딪
    0.41
    ڈیو
    0.40
    ır
    0.39
    neh
    0.39
    දා
    0.39
    indow
    0.39
    ামীর
    0.39
    POSITIVE LOGITS
    parameters
    0.43
     Lloyd
    0.42
     {
    0.38
     ফ
    0.37
     Forum
    0.37
     extortion
    0.37
     Nord
    0.37
     dø
    0.37
    ཡ
    0.36
    弊
    0.36
    Activations Density 0.000%

    No Known Activations