© 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. 176603
    Prev
    Next
    INDEX
    Explanations

    code and commands

    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
    ╴
    0.39
     −/−
    0.39
     H
    0.38
     whit
    0.38
    ່າ
    0.37
    Wilson
    0.37
     빌
    0.37
     ViewModel
    0.37
     Sauna
    0.37
    $\\
    0.37
    POSITIVE LOGITS
    グリ
    0.44
     grij
    0.42
     Essex
    0.40
     Els
    0.39
     Illinois
    0.38
     گل
    0.38
     annexed
    0.38
    gak
    0.38
    lij
    0.37
    alignParent
    0.37
    Activations Density 0.000%

    No Known Activations