© 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. 142768
    Prev
    Next
    INDEX
    Explanations

    places or landmarks

    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
     Sand
    0.62
    沙
    0.62
     沙
    0.60
     Windsor
    0.55
    Sand
    0.52
     Osborne
    0.48
     cle
    0.46
     Bal
    0.46
     Sandler
    0.45
     Frog
    0.44
    POSITIVE LOGITS
     yoj
    0.40
    Gosudarstvennyj
    0.39
     জের
    0.38
    Xr
    0.38
    璜
    0.38
    iyim
    0.37
    ्यानंतर
    0.37
    lık
    0.37
    ameni
    0.36
    ्याची
    0.35
    Activations Density 0.007%

    No Known Activations