© 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. 130177
    Prev
    Next
    INDEX
    Explanations

    ragwort ragga ragman ragas

    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
    يك
    1.00
    人
    0.96
    يل
    0.96
    し
    0.89
    ление
    0.85
    дение
    0.85
    м
    0.84
    وي
    0.81
     لي
    0.80
    يدي
    0.79
    POSITIVE LOGITS
    0
    0.88
     A
    0.86
    f
    0.83
    oh
    0.82
     The
    0.81
     THE
    0.80
     and
    0.79
     R
    0.78
    ired
    0.78
    ên
    0.75
    Activations Density 0.000%

    No Known Activations