© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176146
    Prev
    Next
    INDEX
    Explanations

    places and geography

    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_50_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
     Sek
    0.41
    떠
    0.38
    Sek
    0.38
    SetConfig
    0.37
     cruc
    0.36
     내
    0.36
     tweaking
    0.35
    𝑦
    0.34
    henes
    0.34
     ENGINEERING
    0.33
    POSITIVE LOGITS
     Bernadette
    0.45
     आशीष
    0.44
     మార
    0.44
     Bradley
    0.40
    裴
    0.39
     Ash
    0.39
    COT
    0.38
     Бек
    0.38
     Nashville
    0.38
     Navbar
    0.37
    Activations Density 0.000%

    No Known Activations