© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2391
    Prev
    Next
    INDEX
    Explanations

    mathematical powers and formulas

    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
     plain
    0.42
    Female
    0.40
    })_{
    0.38
     female
    0.37
     എന്നും
    0.37
    iserum
    0.36
     press
    0.35
     broken
    0.35
     Plain
    0.35
    }|\
    0.35
    POSITIVE LOGITS
    ूर्
    0.39
     /**
    0.37
    ଂ
    0.36
    cadherin
    0.35
    ᴼ
    0.35
     supaya
    0.35
     комиссии
    0.35
     공동
    0.35
     наверное
    0.35
    reflectionCamera
    0.34
    Activations Density 0.029%

    No Known Activations