© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-TRANSCODER-262K
    4. 80462
    Prev
    Next
    INDEX
    Explanations

    abbreviations and names

    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
    ding
    0.79
    ds
    0.69
    der
    0.68
    dle
    0.67
    д
    0.66
    d
    0.66
    ԁ
    0.66
    ด์
    0.65
    dings
    0.65
    DING
    0.65
    POSITIVE LOGITS
    しても
    0.41
    না
    0.39
    kangaroo
    0.39
    栦
    0.38
     डायरेक्ट
    0.37
     نامه
    0.37
    ливо
    0.37
    нави
    0.36
     PSD
    0.36
    Nine
    0.36
    Activations Density 0.012%

    No Known Activations