© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138431
    Prev
    Next
    INDEX
    Explanations

    emotionally charged

    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_12_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
     can
    0.62
    f
    0.57
     mè
    0.51
     rosin
    0.49
     innovative
    0.49
     oak
    0.48
    я
    0.48
    artney
    0.47
    㞱
    0.47
    s
    0.47
    POSITIVE LOGITS
     Ради
    0.57
     Там
    0.54
    Todas
    0.54
     Надо
    0.54
    Sink
    0.54
    ങ്
    0.53
    ്രി
    0.53
    োল
    0.52
    cij
    0.51
     Один
    0.51
    Activations Density 0.042%

    No Known Activations