© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231165
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    t
    1.45
    tn
    1.05
    is
    1.02
    the
    1.01
    tive
    1.00
     determ
    0.96
    )
    0.96
    る
    0.93
    tsp
    0.92
    ),
    0.89
    POSITIVE LOGITS
    ęcie
    0.88
    経
    0.86
     Sessions
    0.83
    囩
    0.82
    గానే
    0.80
    oises
    0.80
    多数
    0.79
     بواسطة
    0.76
    лли
    0.72
     Strings
    0.72
    Activations Density 0.000%

    No Known Activations