© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7159
    Prev
    Next
    INDEX
    Explanations

    href="

    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
    ের
    2.61
    runOnUiThread
    2.52
    ات
    2.45
    စိတ်အပိုင်း
    2.36
    ς
    2.34
    referrer
    2.26
    ляется
    2.25
    sigmoid
    2.25
    те
    2.20
    PAD
    2.18
    POSITIVE LOGITS
     renin
    2.75
     einzige
    2.67
     noirâtres
    2.61
     unbedingt
    2.60
     rougeâtres
    2.58
    𝒅
    2.55
     ráp
    2.50
     hassles
    2.49
    ilation
    2.49
     wits
    2.49
    Activations Density 0.000%

    No Known Activations