© 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
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43565
    Prev
    Next
    INDEX
    Explanations

    Alexandre Dumas, rats, death, grain

    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_13_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
     Parece
    0.55
     skute
    0.54
     தொடர்புடைய
    0.53
     Arzneim
    0.52
    鲫
    0.51
     ataques
    0.50
    ્ષ
    0.50
    祛
    0.49
    蘄
    0.49
    会社の
    0.49
    POSITIVE LOGITS
    il
    0.61
    b
    0.61
    ą
    0.59
    ians
    0.58
    innen
    0.54
    ivy
    0.54
    illa
    0.53
    ation
    0.51
    ations
    0.51
    anians
    0.51
    Activations Density 0.000%

    No Known Activations