© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203834
    Prev
    Next
    INDEX
    Explanations

    Journal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    promoting
    0.38
    สึก
    0.37
    탑
    0.37
    ोज़
    0.36
    开展
    0.35
     Prism
    0.34
    hiq
    0.34
    relay
    0.34
    և
    0.33
     ऑफ
    0.33
    POSITIVE LOGITS
     altered
    0.47
     alter
    0.44
     natu
    0.44
     natures
    0.41
     alteration
    0.40
    Nature
    0.39
    Alter
    0.39
    altered
    0.39
     nature
    0.38
    Mutability
    0.37
    Activations Density 0.000%

    No Known Activations