© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228318
    Prev
    Next
    INDEX
    Explanations

    life support systems

    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_6_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
     to
    1.80
    ای
    1.38
    4
    1.27
    ב
    1.23
    д
    1.15
    یک
    1.11
    on
    1.09
    9
    1.09
    5
    1.09
    トラブル
    1.05
    POSITIVE LOGITS
    o
    1.02
    0.96
    و
    0.91
    ين
    0.89
     Papier
    0.84
     見
    0.84
     filer
    0.82
    لي
    0.79
    <0xA7>
    0.77
    ليات
    0.75
    Activations Density 0.000%

    No Known Activations