© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 51425
    Prev
    Next
    INDEX
    Explanations

    comfortable reading chair

    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
     pant
    0.40
    Arts
    0.39
     artista
    0.39
     artistas
    0.38
    ARTS
    0.38
    妖
    0.38
     falar
    0.36
     diá
    0.36
    ন্দ্র
    0.36
    ontal
    0.36
    POSITIVE LOGITS
    ೀರಿ
    0.42
    纺
    0.42
    REGEX
    0.39
     snug
    0.38
     knit
    0.38
    पढ़
    0.38
     strength
    0.37
     cozy
    0.37
     NodeRef
    0.37
    狠狠
    0.37
    Activations Density 0.056%

    No Known Activations