© 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. 61907
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ۰
    1.29
     написа
    1.23
     ਅਤੇ
    1.22
     писа
    1.15
    0
    1.13
     увиде
    1.11
     ίδια
    1.10
    <0x80>
    1.09
    ことなく
    1.09
     اکثر
    1.09
    POSITIVE LOGITS
    "
    2.00
    ي
    1.76
    ”
    1.33
    ت
    1.26
    i
    1.24
    t
    1.18
    d
    1.14
    '
    1.11
     to
    1.10
    ی
    1.10
    Activations Density 0.000%

    No Known Activations