© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90651
    Prev
    Next
    INDEX
    Explanations

    polonium, polyphenylene, polka dots

    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_3_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
     as
    1.17
    L
    0.87
    یس
    0.84
    )،
    0.82
    ،
    0.78
    ра
    0.77
    ट
    0.77
    ’
    0.75
    ב
    0.74
     POSITION
    0.72
    POSITIVE LOGITS
    forschung
    0.66
     поли
    0.65
     empez
    0.63
    f
    0.63
     começ
    0.62
     पोली
    0.62
     înce
    0.60
     изуча
    0.60
    firma
    0.59
     polynom
    0.59
    Activations Density 0.000%

    No Known Activations