© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38590
    Prev
    Next
    INDEX
    Explanations

    frothy substance

    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_3_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
    s
    1.02
    ’
    1.02
     frequ
    0.98
     frequency
    0.94
    dan
    0.92
     frequent
    0.90
     frecuente
    0.87
    ا
    0.87
     fréquent
    0.86
     frecu
    0.84
    POSITIVE LOGITS
    ！)
    0.67
    "。
    0.66
    ש
    0.66
    }">
    0.64
    ق
    0.62
    ⌔
    0.61
    }()
    0.60
     kleinen
    0.59
    "，
    0.58
     因此
    0.58
    Activations Density 0.004%

    No Known Activations