© 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. 200650
    Prev
    Next
    INDEX
    Explanations

    react OR vue or mobx

    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
    da
    0.91
    they
    0.87
    च्या
    0.82
    の頃
    0.82
    nya
    0.79
     quirúrg
    0.78
    ﺻ
    0.78
    ,.
    0.76
    dinga
    0.75
    the
    0.75
    POSITIVE LOGITS
    리
    1.01
    ص
    0.96
    هم
    0.95
    ন
    0.89
    મ
    0.89
    ్ర
    0.88
    ف
    0.88
    تر
    0.83
    ர
    0.82
    ન
    0.81
    Activations Density 0.000%

    No Known Activations