© 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. 5946
    Prev
    Next
    INDEX
    Explanations

    search query

    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
     Subscribers
    0.40
     Дей
    0.38
     kulture
    0.38
     ім
    0.37
    ],
    0.37
    Subscriber
    0.37
     అవ
    0.36
     szak
    0.36
     vastaan
    0.36
    >';
    0.34
    POSITIVE LOGITS
     query
    0.38
    LIED
    0.38
     BAB
    0.36
    leven
    0.36
    Bang
    0.36
    SOR
    0.35
    Gone
    0.35
    mnt
    0.34
     查询
    0.34
    cbc
    0.34
    Activations Density 0.005%

    No Known Activations