© 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. 161416
    Prev
    Next
    INDEX
    Explanations

    willing to help or share

    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
     periód
    0.46
     promptly
    0.43
     timepiece
    0.41
     eagerly
    0.41
    궤
    0.39
     periódico
    0.39
     periodically
    0.38
     웹
    0.38
     प्रशंस
    0.38
    ModuleName
    0.38
    POSITIVE LOGITS
    ährung
    0.36
    塞
    0.35
     Consult
    0.35
    想起
    0.34
    ].)
    0.34
    kt
    0.34
    コーディ
    0.34
     ),
    0.34
     uitle
    0.34
    intr
    0.34
    Activations Density 0.002%

    No Known Activations