© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 149249
    Prev
    Next
    INDEX
    Explanations

    positive continuations after greetings

    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
     nella
    0.59
    ata
    0.59
     l
    0.57
    ida
    0.57
    iks
    0.56
    ish
    0.54
     in
    0.52
    c
    0.52
    ul
    0.51
    th
    0.51
    POSITIVE LOGITS
     समझाया
    0.46
    ABAB
    0.46
    PUB
    0.45
    Both
    0.44
    青春
    0.44
    OLDS
    0.44
    ರಳ
    0.44
     används
    0.43
     소녀
    0.43
    ายุ
    0.43
    Activations Density 0.001%

    No Known Activations