© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161826
    Prev
    Next
    INDEX
    Explanations

    styrene

    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_2_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
    and
    1.00
    ’),
    0.98
    ছিল
    0.94
    ים
    0.94
    ্স
    0.93
    ات
    0.90
    ों
    0.88
    ৫
    0.87
    The
    0.87
     ಹಾಗೂ
    0.86
    POSITIVE LOGITS
    n
    1.27
    ru
    1.25
    ro
    1.21
     for
    1.14
    。
    1.12
     it
    1.01
    mic
    1.00
    ü
    0.98
    ran
    0.97
    ra
    0.96
    Activations Density 0.000%

    No Known Activations