© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34764
    Prev
    Next
    INDEX
    Explanations

    %(asctime)s logging format

    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_31_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
     grada
    0.38
    択
    0.38
    phal
    0.36
     scaleOf
    0.36
     ფ
    0.35
    కర్
    0.35
    鄱
    0.35
    ),]$
    0.35
     trouverez
    0.35
    ytically
    0.35
    POSITIVE LOGITS
    clock
    0.41
     clock
    0.39
    automation
    0.38
    evoluzione
    0.38
     clocked
    0.37
    klu
    0.37
    睡
    0.36
     chronological
    0.36
     मोहन
    0.35
    時計
    0.35
    Activations Density 0.005%

    No Known Activations