© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11023
    Prev
    Next
    INDEX
    Explanations

    New Zealand landmarks and geography

    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_40_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
     Ryu
    0.41
    パッケージ
    0.40
    ihan
    0.39
     Pub
    0.38
     PUB
    0.38
    柔軟
    0.37
     春
    0.36
     partout
    0.35
    伦敦
    0.35
    川
    0.35
    POSITIVE LOGITS
     Auckland
    0.55
     NZ
    0.55
     Wellington
    0.51
    NZ
    0.47
    zun
    0.45
     Dunedin
    0.45
     Otago
    0.45
    ḓ
    0.44
    uckland
    0.41
     Vanuatu
    0.40
    Activations Density 0.015%

    No Known Activations