© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27612
    Prev
    Next
    INDEX
    Explanations

    use environment variables or secrets

    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
     небе
    0.40
     Verte
    0.39
     tecl
    0.38
     adjusted
    0.38
     Biomedical
    0.37
    竝
    0.36
     integrations
    0.36
     adjusting
    0.35
     hoarding
    0.35
    itere
    0.35
    POSITIVE LOGITS
     النق
    0.42
    Rog
    0.40
    larım
    0.38
    Dre
    0.37
    瓯
    0.36
    arlier
    0.35
    Nak
    0.34
    त्रे
    0.34
    namento
    0.34
    洧
    0.34
    Activations Density 0.005%

    No Known Activations