© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3125
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ल
    3.18
    يج
    2.97
    ை
    2.90
    း
    2.82
    ీ
    2.81
     estando
    2.78
     conducir
    2.72
     unreal
    2.71
    
    2.71
     throttle
    2.67
    POSITIVE LOGITS
    ían
    2.64
    ان
    2.54
    ب
    2.52
     ríg
    2.38
    aceous
    2.38
    اء
    2.37
    ly
    2.35
    ทะ
    2.34
    th
    2.33
    смотря
    2.31
    Activations Density 0.067%

    No Known Activations