© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 213476
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs or contractions

    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_16_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
     I
    0.27
    O
    0.26
     comes
    0.25
    being
    0.24
    来
    0.24
    ες
    0.23
     কথায়
    0.23
     involving
    0.23
    来る
    0.23
    A
    0.23
    POSITIVE LOGITS
     kucch
    0.25
    ᠴ
    0.23
     rej
    0.23
     gahet
    0.22
    oré
    0.22
    ியே
    0.22
     sumptuous
    0.22
     ALP
    0.22
     jett
    0.22
    esha
    0.22
    Activations Density 0.023%

    No Known Activations