© 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. 91314
    Prev
    Next
    INDEX
    Explanations

    title, Saturday

    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
    莳
    0.48
    ɔ
    0.47
     chocolates
    0.45
     Sheeran
    0.44
    PCR
    0.43
    Audi
    0.43
    oxic
    0.43
     GDPR
    0.43
     画
    0.42
    awać
    0.42
    POSITIVE LOGITS
    נ
    0.43
    த்து
    0.40
    ئی
    0.39
    ட்டு
    0.39
    ská
    0.38
    skie
    0.38
    க்கி
    0.38
    iski
    0.38
     rumbo
    0.38
    鹘
    0.38
    Activations Density 0.008%

    No Known Activations