© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99185
    Prev
    Next
    INDEX
    Explanations

    guidelines and toolkits

    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_16_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
    parquet
    0.36
    part
    0.33
    ufer
    0.33
    Kata
    0.32
    T
    0.32
    Lu
    0.32
    V
    0.31
    voja
    0.31
    starred
    0.31
    postos
    0.31
    POSITIVE LOGITS
     for
    0.43
    啸
    0.41
    嘯
    0.37
     анг
    0.37
     anglais
    0.36
    ংস
    0.36
    创业
    0.35
    缓解
    0.35
    放松
    0.35
     দিয়াছেন
    0.35
    Activations Density 0.018%

    No Known Activations