© 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. 2390
    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
    鳅
    2.03
     personnelles
    1.81
    ाई
    1.76
    ਨ
    1.69
    ்
    1.69
    britannien
    1.68
    евич
    1.65
    ん
    1.65
    ெடுக்க
    1.61
    tség
    1.61
    POSITIVE LOGITS
    ত্বের
    1.92
    тися
    1.90
    ш
    1.89
    istic
    1.85
     discretion
    1.83
    ды
    1.80
    ত্ব
    1.79
    immune
    1.78
    itarian
    1.77
    ସ
    1.77
    Activations Density 0.022%

    No Known Activations