© 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. 6659
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    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
    
    1.73
    ある
    1.66
     पता
    1.66
     även
    1.65
     quoi
    1.58
    まえ
    1.55
    ে
    1.55
    ků
    1.49
    ५
    1.49
    k
    1.48
    POSITIVE LOGITS
     mascot
    1.28
    িং
    1.21
    nement
    1.14
    hood
    1.13
    лих
    1.09
     segu
    1.08
    А
    1.06
    hashMap
    1.05
     ইহ
    1.04
    មើ
    1.04
    Activations Density 0.261%

    No Known Activations