© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212292
    Prev
    Next
    INDEX
    Explanations

    access point name, network, services

    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_19_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
     meng
    0.24
     ചെയ്യുന്ന
    0.24
     $*
    0.24
     regrett
    0.23
     обита
    0.23
     پردا
    0.23
     montée
    0.23
     Interior
    0.23
     tarea
    0.22
    孟
    0.22
    POSITIVE LOGITS
    Venezuela
    0.29
    kn
    0.27
    Ireland
    0.27
    Tracker
    0.25
    Poland
    0.25
    Russia
    0.25
    utches
    0.25
    list
    0.24
    Belarus
    0.24
    pfl
    0.24
    Activations Density 0.000%

    No Known Activations