© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224952
    Prev
    Next
    INDEX
    Explanations

    mountains, peaks, climbers

    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_10_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
     mountain
    0.97
    .
    0.96
     Mountain
    0.86
    Mountain
    0.86
     $
    0.85
     hill
    0.85
    "
    0.82
     hills
    0.79
    File
    0.79
     mountains
    0.77
    POSITIVE LOGITS
    ség
    0.76
    ме
    0.73
    д
    0.70
    ма
    0.68
    𝗌
    0.67
     compreensão
    0.63
     통한
    0.62
    𝖽
    0.61
    𝘴
    0.60
    データベース
    0.59
    Activations Density 0.013%

    No Known Activations