© 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. 176548
    Prev
    Next
    INDEX
    Explanations

    educational subjects and levels

    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
     poll
    0.47
    ZX
    0.47
     zul
    0.45
    Z
    0.45
     JC
    0.41
     Zul
    0.40
    zx
    0.40
    Zx
    0.39
    zk
    0.39
    郑
    0.39
    POSITIVE LOGITS
     девя
    0.43
    ｹ
    0.39
     turpis
    0.39
     meromorphic
    0.37
    姚
    0.37
    驸
    0.36
     মের
    0.36
    faithful
    0.36
     Grade
    0.36
    <0xBF>
    0.35
    Activations Density 0.001%

    No Known Activations