© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35433
    Prev
    Next
    INDEX
    Explanations

    simulating

    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_11_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
    ד
    0.66
    ྞ
    0.61
     ס
    0.58
     by
    0.56
    ക്‌
    0.55
    کس
    0.55
    ก
    0.52
     க
    0.52
    ק
    0.51
    ן
    0.51
    POSITIVE LOGITS
    u
    0.61
    Ե
    0.56
    稹
    0.54
     જીવન
    0.53
     जीवन
    0.52
     삶
    0.50
     Mej
    0.49
    토리
    0.49
    た
    0.49
    reso
    0.49
    Activations Density 0.012%

    No Known Activations