© 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. 91144
    Prev
    Next
    INDEX
    Explanations

    Mad science or queen

    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
     ряда
    0.78
    䬲
    0.67
    ين
    0.66
     legitim
    0.63
     problém
    0.60
     Forrester
    0.60
     яких
    0.59
     موسي
    0.59
     ليست
    0.58
     работа
    0.57
    POSITIVE LOGITS
    ли
    0.91
    3
    0.89
    る
    0.78
    ३
    0.77
    li
    0.77
    ती
    0.77
     uncovering
    0.74
    ll
    0.71
    weaving
    0.69
    d
    0.69
    Activations Density 0.000%

    No Known Activations