© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226477
    Prev
    Next
    INDEX
    Explanations

    off the

    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_6_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
    I
    1.13
     I
    0.98
     یک
    0.89
    oka
    0.84
     </
    0.83
    <0x0D>
    0.82
    oped
    0.80
    zan
    0.80
    .</
    0.79
    ija
    0.79
    POSITIVE LOGITS
    다는
    1.17
    ين
    1.14
    ד
    1.09
    ية
    1.06
     be
    1.05
    ку
    1.05
    ות
    1.02
    ت
    1.02
     discriminant
    1.01
    هم
    1.00
    Activations Density 0.001%

    No Known Activations