© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7552
    Prev
    Next
    INDEX
    Explanations

    log n complexity

    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_40_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
    bcd
    0.38
    澄清
    0.34
    俸
    0.34
    Tal
    0.34
     tal
    0.33
    ➚
    0.33
     adjuvant
    0.32
    謄
    0.32
    সপ
    0.32
     సాం
    0.32
    POSITIVE LOGITS
     линей
    0.49
     linear
    0.47
     lineales
    0.45
     Linear
    0.43
     linearly
    0.43
     linearity
    0.39
    線性
    0.39
    Linear
    0.39
    linear
    0.37
     lineal
    0.36
    Activations Density 0.002%

    No Known Activations