© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107313
    Prev
    Next
    INDEX
    Explanations

    Cup (2023) franchise Gundam

    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
    c
    1.07
    もら
    0.96
     vocation
    0.95
     gastronomic
    0.94
    리로
    0.92
    ূতন
    0.91
     செல்சிய
    0.91
    が多い
    0.91
    ो
    0.91
     as
    0.89
    POSITIVE LOGITS
    I
    1.38
    ز
    1.27
    к
    1.10
    ی
    1.09
    م
    1.09
    ین
    1.00
    ю
    0.99
    اه
    0.95
     asesin
    0.95
    </sup>
    0.95
    Activations Density 0.000%

    No Known Activations