© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197957
    Prev
    Next
    INDEX
    Explanations

    intrinsically magnetic

    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
    Negative Logits
     to
    0.63
     -
    0.55
    orer
    0.54
    own
    0.52
    ahl
    0.51
    ueil
    0.51
    out
    0.50
    苦
    0.50
    orno
    0.49
     el
    0.48
    POSITIVE LOGITS
     capelli
    0.65
     haird
    0.59
    ヘア
    0.58
     Freude
    0.58
    žky
    0.58
     Freiheit
    0.57
     Amiri
    0.57
     korišten
    0.56
     backseat
    0.56
     ஜீய
    0.55
    Activations Density 0.000%

    No Known Activations