© 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. 3083
    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
    ş
    2.78
    𝘢
    2.43
    να
    2.40
    socket
    2.40
    क्रम
    2.33
    িকাংশ
    2.32
    п
    2.26
    तुर
    2.25
     fertilized
    2.24
    inal
    2.24
    POSITIVE LOGITS
    اب
    3.30
     textField
    2.55
    गें
    2.49
    າມາດ
    2.48
    ie
    2.45
     Cabo
    2.43
     clf
    2.37
     απο
    2.37
    ل
    2.34
    પણે
    2.32
    Activations Density 0.064%

    No Known Activations