© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195680
    Prev
    Next
    INDEX
    Explanations

    chart types

    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_4_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
    ться
    1.16
    ى
    1.14
    ും
    1.06
    ل
    1.02
    𝕖
    1.02
    ль
    1.00
    сист
    1.00
    مل
    0.98
    ون
    0.97
    تش
    0.97
    POSITIVE LOGITS
     has
    1.02
    "
    0.98
     is
    0.95
    場合
    0.88
    ",
    0.87
    iswa
    0.84
    \
    0.82
     i
    0.81
     de
    0.80
     Eve
    0.80
    Activations Density 0.002%

    No Known Activations