© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    4. 106186
    Prev
    Next
    INDEX
    Explanations

    bonanza, senpai

    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_1_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
    การ
    0.96
     χρήση
    0.94
    ,.
    0.92
     договору
    0.92
     време
    0.90
    )^{*}
    0.89
     tonne
    0.88
     vaporization
    0.88
     дает
    0.87
    ,»
    0.84
    POSITIVE LOGITS
    in
    2.23
    to
    1.88
    t
    1.85
    f
    1.63
    m
    1.61
    at
    1.55
    y
    1.53
    on
    1.51
    ta
    1.45
    i
    1.45
    Activations Density 0.000%

    No Known Activations