© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102286
    Prev
    Next
    INDEX
    Explanations

    symbiotic algae, bacterium, control programs

    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_14_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
    AUC
    0.47
    ？」
    0.47
    EC
    0.46
    скільки
    0.46
    Denominator
    0.46
     Дан
    0.46
    ？？
    0.46
    ྵ
    0.46
     ?$
    0.45
    surgery
    0.45
    POSITIVE LOGITS
     n
    0.62
     Prayer
    0.55
    ik
    0.55
    illon
    0.55
     Prayers
    0.55
     prayers
    0.53
     prayer
    0.52
    ita
    0.51
    লাপ
    0.51
     Millennials
    0.51
    Activations Density 0.000%

    No Known Activations