© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30461
    Prev
    Next
    INDEX
    Explanations

    australia, pter followed by comma or separator

    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_7_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
     Объ
    0.21
     그렇
    0.20
    t
    0.20
     adduced
    0.20
     জানান
    0.19
     рядом
    0.19
    et
    0.18
     Berikut
    0.18
    <0x96>
    0.18
     pokazuje
    0.18
    POSITIVE LOGITS
    的
    0.31
     be
    0.28
     of
    0.27
    生物
    0.24
    وف
    0.24
     as
    0.24
    نت
    0.23
    ق
    0.23
     تت
    0.23
    3
    0.22
    Activations Density 0.001%

    No Known Activations