© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80212
    Prev
    Next
    INDEX
    Explanations

    state of readiness

    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_31_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
     አስተ
    0.37
     développ
    0.37
    が存在
    0.36
     চির
    0.35
    发达
    0.35
     gov
    0.35
    )$$
    0.35
    徳
    0.34
     बनाती
    0.34
    шим
    0.34
    POSITIVE LOGITS
     ready
    1.35
    ready
    1.20
     Ready
    1.18
    Ready
    1.17
     READY
    1.07
     готова
    1.04
    READY
    1.01
     آماده
    1.00
     готов
    1.00
     klaar
    0.99
    Activations Density 0.042%

    No Known Activations