© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161952
    Prev
    Next
    INDEX
    Explanations

    high quality

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Tar
    0.24
    extraction
    0.23
     tarif
    0.23
     Hindustan
    0.23
     contempl
    0.22
     ٹک
    0.22
     prit
    0.22
    忿
    0.22
    examination
    0.22
    Public
    0.22
    POSITIVE LOGITS
     calidad
    0.35
    Quality
    0.34
     Quality
    0.34
     quality
    0.34
     kaliteli
    0.33
     Qualitäts
    0.32
     QUALITY
    0.32
     качество
    0.31
     chất
    0.31
     qualidade
    0.31
    Activations Density 0.006%

    No Known Activations