© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58922
    Prev
    Next
    INDEX
    Explanations

    say "I"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    채
    0.59
    รง
    0.54
     채
    0.52
    책
    0.50
    ร
    0.50
     ร
    0.48
    ड
    0.48
    รก
    0.46
    ย
    0.45
    端
    0.44
    POSITIVE LOGITS
     &#
    1.09
     �
    1.05
     Ã
    0.95
    &#
    0.88
    �
    0.86
    ��������
    0.85
    ����
    0.83
     â
    0.80
     ï
    0.77
    ���
    0.77
    Activations Density 0.005%

    No Known Activations