© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171838
    Prev
    Next
    INDEX
    Explanations

    grid columns

    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_20_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
     ذلك
    0.26
    you
    0.26
     itu
    0.26
    ino
    0.25
    특히
    0.25
    잘
    0.25
    Disney
    0.25
    פה
    0.25
    系統
    0.25
    oth
    0.24
    POSITIVE LOGITS
     apprehend
    0.34
    ↦
    0.33
     separates
    0.32
     SHEET
    0.30
    ଁ
    0.30
     longing
    0.30
     Sada
    0.30
     dbc
    0.30
     kamera
    0.29
     kms
    0.29
    Activations Density 0.000%

    No Known Activations