© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63751
    Prev
    Next
    INDEX
    Explanations

    connect, resonate, foster, evoke

    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_41_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
     sealed
    0.45
     changing
    0.42
     leave
    0.39
     گذا
    0.38
     BE
    0.38
     Changing
    0.38
    </
    0.37
     changes
    0.36
     Expect
    0.36
     cover
    0.35
    POSITIVE LOGITS
    ത്തര
    0.43
     ∀
    0.38
     정도
    0.37
    EnumType
    0.37
    故事
    0.36
     trialComponents
    0.36
     gtag
    0.35
     stateMutability
    0.35
     করেছেন
    0.35
     conexiones
    0.35
    Activations Density 0.004%

    No Known Activations