© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3962
    Prev
    Next
    INDEX
    Explanations

    way to

    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_40_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
    imbulkan
    0.24
     traite
    0.23
    녕하세요
    0.21
    首歌
    0.21
    Structures
    0.20
    帘
    0.20
    牪
    0.20
    ).'
    0.20
     Treatise
    0.19
    扱う
    0.19
    POSITIVE LOGITS
     doing
    0.21
    rell
    0.21
     Doing
    0.21
    amines
    0.20
    ເຂົ້າ
    0.20
     responsáveis
    0.20
     manda
    0.20
     पारस्परिक
    0.20
     responsible
    0.20
    するための
    0.20
    Activations Density 0.000%

    No Known Activations