© 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. 161441
    Prev
    Next
    INDEX
    Explanations

    charge and recharge time

    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
    Negative Logits
    Parks
    0.45
    parks
    0.41
     cementing
    0.40
     parks
    0.36
    cephalus
    0.35
     зимо
    0.35
    ⌝
    0.35
    anium
    0.35
     Parks
    0.35
     пье
    0.35
    POSITIVE LOGITS
    滚
    0.44
     Penal
    0.40
     uruch
    0.38
     Pemb
    0.38
     Blob
    0.38
     nascost
    0.36
     سزا
    0.36
     RELEASE
    0.36
     آزادی
    0.35
    発売
    0.35
    Activations Density 0.002%

    No Known Activations