© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 129810
    Prev
    Next
    INDEX
    Explanations

    class names and states

    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_25_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
    ParaName
    0.15
    Platz
    0.14
    Proveedor
    0.13
    ProductId
    0.13
    ający
    0.13
     ಸಂಗ
    0.12
    酐
    0.12
    흄
    0.12
    ார்
    0.12
    getParent
    0.12
    POSITIVE LOGITS
     l
    0.16
     considerable
    0.15
     extensively
    0.15
     deu
    0.15
     study
    0.15
     examine
    0.15
     cautiously
    0.15
     super
    0.14
     go
    0.14
     re
    0.14
    Activations Density 0.003%

    No Known Activations