© 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. 3652
    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
    ীয়
    2.87
     bă
    2.79
     pakai
    2.79
    %)
    2.37
     suceder
    2.34
    ½
    2.33
    يك
    2.30
    ইয়া
    2.27
     зда
    2.27
    वर्ती
    2.26
    POSITIVE LOGITS
    র
    3.56
    ד
    3.12
    𝖽
    2.86
    𝘤
    2.66
    cargar
    2.64
    स
    2.63
    𝘷
    2.51
    ᚑ
    2.49
    धानिक
    2.45
    스팅
    2.44
    Activations Density 0.011%

    No Known Activations