© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234242
    Prev
    Next
    INDEX
    Explanations

    Middle East policy and Israel

    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_32_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
     ജന
    0.38
     corridor
    0.35
    承認
    0.35
    òa
    0.34
    ",[],
    0.34
     অবরোধ
    0.33
    реже
    0.33
    Quadr
    0.33
    anni
    0.33
    ['_
    0.33
    POSITIVE LOGITS
     fuerza
    0.38
    England
    0.38
    豺
    0.38
     बल
    0.37
     pressur
    0.36
     $^{
    0.36
     Burma
    0.36
    សម្រ
    0.35
     trom
    0.35
     pressurized
    0.35
    Activations Density 0.001%

    No Known Activations