© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23243
    Prev
    Next
    INDEX
    Explanations

    collecting

    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_56_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
     अमल
    0.36
    渋
    0.34
    роме
    0.33
     गिरफ्त
    0.32
    ຖື
    0.32
    烪
    0.32
    ុក
    0.32
    おい
    0.32
     اهلا
    0.31
    ையைப்
    0.31
    POSITIVE LOGITS
     collection
    2.98
    collection
    2.81
     Collection
    2.80
     collect
    2.77
     колек
    2.72
     kolek
    2.69
    Collection
    2.67
     kole
    2.66
     коллек
    2.66
     collecting
    2.61
    Activations Density 0.022%

    No Known Activations