© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125308
    Prev
    Next
    INDEX
    Explanations

    here's the thing, weather, attempt

    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
    ق
    0.83
    在
    0.79
    س
    0.71
     Ground
    0.59
    ও
    0.59
    ือ
    0.59
    도
    0.57
     entendu
    0.57
    ف
    0.56
     우리나라
    0.56
    POSITIVE LOGITS
    ig
    0.69
    that
    0.66
    ﺎ
    0.66
     that
    0.61
    𝓇
    0.60
    𝚆
    0.59
     Gauss
    0.57
    arı
    0.57
    itre
    0.57
    l
    0.57
    Activations Density 0.005%

    No Known Activations