© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159716
    Prev
    Next
    INDEX
    Explanations

    remains unchanged

    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
    ר
    1.40
    r
    1.22
    ur
    1.08
    ط
    1.00
    رات
    0.98
    ד
    0.98
    లై
    0.96
    ről
    0.92
    لية
    0.92
    ర
    0.91
    POSITIVE LOGITS
    し
    1.13
    gunakan
    1.09
     dichiar
    1.08
    <0x80>
    1.05
     retorn
    1.04
    pengaruhi
    1.04
    t
    1.04
    chi
    1.02
    cretion
    1.02
    of
    1.01
    Activations Density 0.001%

    No Known Activations