© 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
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159827
    Prev
    Next
    INDEX
    Explanations

    spacefaring civilizations

    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_2_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
     on
    1.52
    N
    1.21
     yıllık
    1.13
     ilk
    1.10
    D
    1.10
    S
    1.08
    त
    1.06
    দের
    1.05
    on
    1.04
    ne
    1.04
    POSITIVE LOGITS
    िक
    1.36
    ز
    1.23
    ess
    1.16
    ться
    1.15
    ust
    1.13
    0.98
    icier
    0.97
    ic
    0.92
    ጨማሪ
    0.92
    bere
    0.91
    Activations Density 0.001%

    No Known Activations