© 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. 108338
    Prev
    Next
    INDEX
    Explanations

    organiza, utiliza

    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
    ي
    1.75
    an
    1.67
    ت
    1.49
     ugljik
    1.27
     формат
    1.24
    럏
    1.21
     спорттук
    1.20
    ἲ
    1.19
    iş
    1.17
    т
    1.17
    POSITIVE LOGITS
    </h2>
    1.38
    s
    1.38
    5
    1.34
    <0x0D>
    1.32
    2
    1.24
    ции
    1.12
    %)
    1.09
     was
    1.08
    4
    1.06
    </u>
    1.05
    Activations Density 0.001%

    No Known Activations