© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76507
    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_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
     сег
    0.41
    땅
    0.41
     produkcji
    0.39
    搐
    0.39
     geben
    0.39
    ជូន
    0.38
    databases
    0.38
     databases
    0.37
     grupos
    0.37
    を踏
    0.36
    POSITIVE LOGITS
    ابق
    0.41
     reverse
    0.39
     reverses
    0.37
    😜
    0.37
     previous
    0.37
    MeOH
    0.36
     reversing
    0.36
    versal
    0.36
     Sebelumnya
    0.36
     accumulation
    0.36
    Activations Density 0.000%

    No Known Activations