© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93035
    Prev
    Next
    INDEX
    Explanations

    then ... forces, iron, the, to, conquer, and

    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_11_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
     d
    0.77
     t
    0.75
     U
    0.67
    U
    0.66
    mid
    0.66
    vers
    0.65
    ac
    0.64
    workers
    0.64
    burn
    0.61
     c
    0.59
    POSITIVE LOGITS
    ListItemIcon
    0.61
     integrante
    0.57
     validations
    0.57
     actitudes
    0.54
     necesitamos
    0.54
     crítico
    0.54
    ்ட்ட
    0.52
     parâmetros
    0.51
    နဲ့
    0.51
    ่อย
    0.50
    Activations Density 0.007%

    No Known Activations