© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45061
    Prev
    Next
    INDEX
    Explanations

    minecraft smp servers

    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_13_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
    M
    0.42
    l
    0.38
     rumoured
    0.38
    dagger
    0.38
    オ
    0.37
    女儿
    0.36
    })^{\
    0.36
    デバイス
    0.36
    icosia
    0.35
     l
    0.35
    POSITIVE LOGITS
     Мен
    0.44
     Bismillahirrah
    0.44
    탉
    0.43
     він
    0.43
     Кон
    0.42
    omist
    0.41
     vab
    0.40
    Bracketing
    0.40
    èmes
    0.39
     Brü
    0.38
    Activations Density 0.005%

    No Known Activations