© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64720
    Prev
    Next
    INDEX
    Explanations

    service

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    puppet
    0.38
    谴
    0.38
     চু
    0.37
    KeyValuePair
    0.37
    추
    0.37
    rion
    0.37
    راءة
    0.37
     অঙ্গীকার
    0.37
    త్త
    0.36
    咙
    0.36
    POSITIVE LOGITS
     servici
    1.19
     palvel
    1.13
    服务
    1.12
     servicios
    1.12
     serve
    1.10
     hizmet
    1.09
     services
    1.09
     served
    1.09
     serviço
    1.09
    服務
    1.07
    Activations Density 0.005%

    No Known Activations