© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242961
    Prev
    Next
    INDEX
    Explanations

    list of terms

    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_40_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
     coloring
    0.42
     kleur
    0.41
    zieh
    0.39
    :')
    0.39
    :'],
    0.38
     vâ
    0.38
    myp
    0.38
     DIE
    0.37
    ਿਹ
    0.37
     '),
    0.36
    POSITIVE LOGITS
     جميع
    0.38
    zeczytaj
    0.35
     Anil
    0.35
     Implications
    0.34
     તેના
    0.34
     Depos
    0.34
     All
    0.33
     implications
    0.33
     南
    0.33
     Пор
    0.32
    Activations Density 0.005%

    No Known Activations