© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80166
    Prev
    Next
    INDEX
    Explanations

    при followed by context words

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases and terms related to historical or political topics.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi

    при

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     Exhibition
    0.31
     —
    0.29
    L
    0.29
     mong
    0.28
     Legs
    0.28
     chú
    0.28
     initi
    0.27
     aktiv
    0.27
    <0xB2>
    0.27
     oi
    0.27
    POSITIVE LOGITS
     Porém
    0.32
    刚
    0.31
     ประก
    0.30
     {});
    0.29
    ುತ್ತಿದೆ
    0.29
     hermoso
    0.29
     అయినా
    0.28
     njeg
    0.28
    동산
    0.28
    웬
    0.28
    Activations Density 0.001%

    No Known Activations