© 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. 100375
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    謦
    0.54
    ্ত
    0.51
    ご購入
    0.49
    מצע
    0.48
    দানে
    0.48
    ંદ
    0.46
    芢
    0.46
     אבי
    0.45
    ্দি
    0.45
    ቲክ
    0.45
    POSITIVE LOGITS
    ,
    0.48
     به
    0.47
    liess
    0.46
     times
    0.46
    f
    0.46
    se
    0.44
    eben
    0.44
     Р
    0.43
    vel
    0.43
     Grenz
    0.42
    Activations Density 0.000%

    No Known Activations