© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 51457
    Prev
    Next
    INDEX
    Explanations

    investigating news and crime

    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_31_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
     icc
    0.38
     Pants
    0.38
     Greenwich
    0.36
     vc
    0.36
     Copies
    0.36
    hrt
    0.36
    ्यान
    0.35
    栽
    0.35
    vc
    0.34
     copies
    0.34
    POSITIVE LOGITS
     डेब्यू
    0.36
    angleOf
    0.34
     продукты
    0.33
    威胁
    0.33
     হলে
    0.32
     контек
    0.32
    瑉
    0.32
    sgd
    0.32
     alps
    0.32
     Infantil
    0.32
    Activations Density 0.001%

    No Known Activations