© 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. 63577
    Prev
    Next
    INDEX
    Explanations

    Iberian Peninsula

    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
    mii
    0.41
    奉
    0.39
    Skirt
    0.39
    انس
    0.36
     devise
    0.35
     Hook
    0.35
    uint
    0.34
     generosity
    0.34
    នោះ
    0.34
    especially
    0.34
    POSITIVE LOGITS
    邛
    0.38
    শিপ
    0.37
     മത
    0.37
     റ
    0.37
     ජ
    0.36
    变更
    0.36
     Ř
    0.36
    రుగులు
    0.36
     jabatan
    0.36
    Reactive
    0.36
    Activations Density 0.000%

    No Known Activations