© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80978
    Prev
    Next
    INDEX
    Explanations

    Objective:

    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
     fluid
    0.34
    流
    0.34
    Shake
    0.33
    astics
    0.32
     Fluid
    0.32
    Fluid
    0.32
    edas
    0.32
    ount
    0.32
     prompted
    0.31
    xls
    0.31
    POSITIVE LOGITS
     tamaño
    0.39
     هدف
    0.38
    ंदरे
    0.37
    䟺
    0.37
     esencia
    0.36
     استعداد
    0.36
    هدف
    0.36
     사이즈
    0.35
     размер
    0.35
     Größe
    0.35
    Activations Density 0.007%

    No Known Activations