© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227049
    Prev
    Next
    INDEX
    Explanations

    karst limestone formations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
     Khi
    0.96
    ﺃ
    0.95
     Yeni
    0.92
     Üniversitesi
    0.91
     Yönet
    0.90
     Kasım
    0.89
     Eğer
    0.87
     Poet
    0.86
     Sekolah
    0.86
     Pawar
    0.86
    POSITIVE LOGITS
    on
    1.22
    ای
    1.18
     exemples
    0.93
    리와
    0.92
     essences
    0.89
    리
    0.88
    onin
    0.86
     classifications
    0.85
    us
    0.84
    ف
    0.82
    Activations Density 0.000%

    No Known Activations