© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145598
    Prev
    Next
    INDEX
    Explanations

    5

    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_59_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
     sharp
    0.50
     U
    0.44
    7
    0.41
     t
    0.39
     research
    0.39
    To
    0.38
    9
    0.38
     cylinder
    0.38
     hot
    0.38
    Sharp
    0.38
    POSITIVE LOGITS
     p
    0.59
    p
    0.56
     pTM
    0.54
     NAM
    0.44
     п
    0.44
    NAM
    0.43
    𝑝
    0.43
    ERING
    0.43
     ENEM
    0.42
    ZR
    0.42
    Activations Density 0.000%

    No Known Activations