© 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. 195096
    Prev
    Next
    INDEX
    Explanations

    0

    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
     Regeln
    0.39
    galkan
    0.39
     vials
    0.39
    ينات
    0.37
    ủa
    0.37
     ketones
    0.37
    ניים
    0.37
     ･
    0.36
    тивних
    0.36
     ທ
    0.36
    POSITIVE LOGITS
     DP
    0.41
     temporally
    0.39
     pariy
    0.38
    Hier
    0.37
     수도
    0.37
    وش
    0.37
    umbu
    0.36
    QSizePolicy
    0.36
    Occupation
    0.35
    lass
    0.35
    Activations Density 0.005%

    No Known Activations