© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82595
    Prev
    Next
    INDEX
    Explanations

    numerical values

    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_53_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
     ನೀರಿನ
    0.42
     sorta
    0.40
     \,\
    0.40
     Whats
    0.39
     headset
    0.38
    烘
    0.38
     singlet
    0.38
    Andreas
    0.37
    吅
    0.37
    ソン
    0.37
    POSITIVE LOGITS
     سعی
    0.34
     reúne
    0.33
    ęt
    0.32
     erros
    0.32
    ताएं
    0.32
     đây
    0.32
    툭
    0.31
    ilmiş
    0.31
    ❢
    0.31
    痉
    0.31
    Activations Density 0.004%

    No Known Activations