© 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
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206706
    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_25_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
     شاء
    0.41
     bölges
    0.39
    Periph
    0.39
    说了
    0.39
     اول
    0.38
    NeedConnect
    0.37
     ऑपरेशन
    0.37
    ১
    0.37
     takım
    0.36
    agation
    0.36
    POSITIVE LOGITS
     তৎ
    0.38
     திரு
    0.37
    hell
    0.37
     bins
    0.36
    trn
    0.35
     vast
    0.33
     therapeutic
    0.33
     -
    0.33
     fairer
    0.33
    anti
    0.33
    Activations Density 0.000%

    No Known Activations