© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37755
    Prev
    Next
    INDEX
    Explanations

    guessing game prompts

    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_11_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
    гляда
    0.41
     CEF
    0.40
     જાય
    0.40
     involved
    0.39
    𝑀
    0.39
    mnu
    0.38
     govern
    0.37
    যাপন
    0.37
    رافی
    0.37
    джер
    0.37
    POSITIVE LOGITS
     plantes
    0.41
    }}-\
    0.41
    auks
    0.38
     {
    0.38
    ach
    0.37
     tacos
    0.37
     presento
    0.37
     Karel
    0.37
     meille
    0.36
    antra
    0.36
    Activations Density 0.025%

    No Known Activations