© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51471
    Prev
    Next
    INDEX
    Explanations

    design and technical terms

    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_30_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
     distracting
    0.46
    ⇰
    0.42
     adults
    0.42
     distractions
    0.40
     transgenic
    0.39
     temptations
    0.39
    Fel
    0.39
     lanceol
    0.39
     enchanting
    0.38
     regimes
    0.37
    POSITIVE LOGITS
     ​​
    0.42
    foro
    0.39
     ​​​​
    0.39
    木
    0.39
    谦
    0.38
     Version
    0.38
    ​​​​
    0.38
     PTFE
    0.38
     MADE
    0.38
    markdown
    0.37
    Activations Density 0.019%

    No Known Activations