© 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. 147032
    Prev
    Next
    INDEX
    Explanations

    AI technical discussions

    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
    Next
    0.41
     저는
    0.39
     både
    0.38
    El
    0.38
     tôi
    0.38
    Saya
    0.37
    我
    0.37
     나는
    0.36
    अग
    0.36
     SSI
    0.36
    POSITIVE LOGITS
    �
    0.74
    ��
    0.73
     �
    0.68
    ��������
    0.64
    ����
    0.62
    ���
    0.58
    <unused61>
    0.54
    <unused62>
    0.43
    <unused60>
    0.42
    toFixed
    0.41
    Activations Density 0.000%

    No Known Activations