© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168445
    Prev
    Next
    INDEX
    Explanations

    English Channel and Turkish Straits passages

    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_34_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
    venv
    0.43
     pname
    0.39
     পড়ছে
    0.38
    ouncing
    0.37
     coconut
    0.36
     Đế
    0.35
    Polling
    0.35
    ᱥ
    0.35
    ത്തിലേ
    0.34
     Urine
    0.34
    POSITIVE LOGITS
     ferry
    0.49
     ferries
    0.48
     crossings
    0.47
     Ferry
    0.46
     Dover
    0.44
     Straits
    0.43
     crossing
    0.42
     conspired
    0.41
     Fermi
    0.41
     Crossing
    0.41
    Activations Density 0.001%

    No Known Activations