© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13524
    Prev
    Next
    INDEX
    Explanations

    Kingdoms

    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_15_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
     Ia
    0.61
     ia
    0.51
     Immediate
    0.51
     Deine
    0.51
    0
    0.50
     ))
    0.50
     .
    0.50
     io
    0.50
     Deze
    0.49
     Have
    0.48
    POSITIVE LOGITS
    imani
    0.59
    𝗠
    0.58
    𝙇
    0.56
    Marble
    0.54
    𝗟
    0.54
    𝒍
    0.53
    âte
    0.52
    મ
    0.52
    ुलेंस
    0.52
    üm
    0.52
    Activations Density 0.000%

    No Known Activations