© 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. 48074
    Prev
    Next
    INDEX
    Explanations

    steel rim

    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
    tir
    0.38
    **:
    0.38
    bond
    0.37
    ’:
    0.36
    '):
    0.36
     Rach
    0.35
    ी
    0.35
    year
    0.34
     kèm
    0.34
     "":
    0.33
    POSITIVE LOGITS
     संतुल
    0.37
     จัด
    0.36
     forgets
    0.35
     outsourcing
    0.35
    цыі
    0.35
     مقدم
    0.34
    ۱۹
    0.34
    তিপ
    0.34
     खिला
    0.34
    forget
    0.33
    Activations Density 0.000%

    No Known Activations