© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    4. 99458
    Prev
    Next
    INDEX
    Explanations

    desire or need for something

    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_14_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
    }}^{\
    0.57
    ท
    0.52
     convient
    0.50
    ку
    0.49
    к
    0.49
     جہاں
    0.48
    有什么
    0.47
    cepción
    0.46
     ин
    0.46
     pensamento
    0.46
    POSITIVE LOGITS
    Tree
    0.52
     Росії
    0.48
    ➊
    0.48
     Tree
    0.47
     Европы
    0.47
    cD
    0.46
     للش
    0.46
    isation
    0.45
    te
    0.44
    OSPHER
    0.44
    Activations Density 0.000%

    No Known Activations