© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54601
    Prev
    Next
    INDEX
    Explanations

    not all

    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_31_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
    extremely
    0.37
     stain
    0.33
    +,
    0.32
     sometimes
    0.32
    بعض
    0.32
     খুবই
    0.30
     tuyên
    0.30
    ১
    0.30
    immune
    0.30
    пят
    0.30
    POSITIVE LOGITS
    組合
    0.37
     Combin
    0.34
     combinations
    0.33
     combo
    0.33
     обязательно
    0.33
     combinação
    0.33
     combina
    0.32
     alterações
    0.32
    するには
    0.31
     combinaison
    0.31
    Activations Density 0.005%

    No Known Activations