© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 4766
    Prev
    Next
    INDEX
    Explanations

    three

    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_44_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
    Ex
    0.25
    gener
    0.22
    P
    0.22
    paste
    0.21
    LI
    0.21
     Succ
    0.20
    8
    0.20
    텔
    0.20
     Rep
    0.20
    A
    0.20
    POSITIVE LOGITS
     trzech
    0.31
     তিনটি
    0.29
     drie
    0.29
     három
    0.29
     drei
    0.29
    elevationMap
    0.28
     তিনটা
    0.28
     tři
    0.27
     trois
    0.27
     três
    0.27
    Activations Density 0.005%

    No Known Activations