© 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. 130347
    Prev
    Next
    INDEX
    Explanations

    long run

    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
    ین
    0.83
    to
    0.83
    c
    0.80
    tetra
    0.76
    کنند
    0.75
     اکنون
    0.73
    各地
    0.73
    Очень
    0.73
    К
    0.73
    Одна
    0.72
    POSITIVE LOGITS
    ue
    0.84
    ని
    0.83
    اية
    0.79
    ا
    0.78
    ру
    0.77
    3
    0.77
    ä
    0.76
    ᱓
    0.76
    í
    0.75
     bevor
    0.74
    Activations Density 0.000%

    No Known Activations