© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8363
    Prev
    Next
    INDEX
    Explanations

    want to feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_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
    swering
    2.15
    en
    2.08
    ০০০
    1.98
     retinopathy
    1.93
    ित
    1.91
    খানেই
    1.86
    ن
    1.85
    ங்கிணை
    1.85
     onSuccess
    1.85
    <unused2121>
    1.83
    POSITIVE LOGITS
    𝕣
    1.93
    াদ
    1.71
    اگر
    1.70
    ★★
    1.68
     cope
    1.66
    ்
    1.61
     ব্রিগে
    1.61
     rectify
    1.61
    સ
    1.59
     piedi
    1.57
    Activations Density 0.015%

    No Known Activations