© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    4. 148483
    Prev
    Next
    INDEX
    Explanations

    series and products

    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_18_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
     yawning
    0.26
     typeface
    0.22
    नॉ
    0.22
     новым
    0.22
    安
    0.22
     źród
    0.22
    芬
    0.22
    \{-\
    0.21
     Grâce
    0.21
    ďaka
    0.21
    POSITIVE LOGITS
     cookbooks
    0.22
    uche
    0.22
     In
    0.22
    criptor
    0.21
     જાણી
    0.21
     Publications
    0.21
    ppro
    0.21
    b
    0.21
    Concent
    0.20
     che
    0.20
    Activations Density 0.015%

    No Known Activations