© 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. 150948
    Prev
    Next
    INDEX
    Explanations

    发

    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
    觓
    0.39
     experiencing
    0.38
     mengalami
    0.38
    ানুভূতি
    0.37
     체험
    0.36
    ార్థ
    0.35
     berj
    0.35
     rejuvenation
    0.34
    ITIS
    0.34
    दर्शी
    0.34
    POSITIVE LOGITS
    发
    0.57
    作
    0.56
    發
    0.49
    奇
    0.47
     il
    0.46
    发的
    0.45
    చి
    0.43
    犯
    0.43
    春
    0.41
    newpage
    0.40
    Activations Density 0.000%

    No Known Activations