© 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. 3700
    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
    রে
    2.81
    لا
    2.75
    ক
    2.53
    الم
    2.47
    atia
    2.46
    asilkan
    2.43
    𝐞
    2.41
    (\
    2.39
     mener
    2.35
    गांव
    2.35
    POSITIVE LOGITS
    ا
    2.86
    اية
    2.81
    া
    2.78
    জ
    2.76
    ]);
    2.70
    要
    2.68
    ป์
    2.62
    द
    2.51
    дцать
    2.45
    
    2.43
    Activations Density 0.052%

    No Known Activations