© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7505
    Prev
    Next
    INDEX
    Explanations

    @Autowired private

    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_39_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
    Calcium
    0.38
     потра
    0.37
    試
    0.36
     Try
    0.35
     Hø
    0.35
     تص
    0.35
    Try
    0.35
     filtration
    0.34
    试
    0.34
     packed
    0.34
    POSITIVE LOGITS
    private
    0.44
     ماد
    0.42
     private
    0.41
    ⿹
    0.39
    incial
    0.38
     મદ
    0.37
    优先级
    0.37
     versiones
    0.37
     privés
    0.37
     reset
    0.36
    Activations Density 0.002%

    No Known Activations