© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 102
    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
    न
    2.86
    й
    2.43
    ع
    2.29
    age
    2.26
    तः
    2.25
    お客
    2.18
    加坡
    2.14
    %%%%%%%%%%%%
    2.13
    𝐷
    2.12
    y
    2.11
    POSITIVE LOGITS
    terrain
    2.47
     bầu
    2.36
     Sicher
    2.11
    ați
    2.07
     snatch
    2.04
     aldosterone
    2.02
     hề
    2.00
    缥
    2.00
    స్
    1.98
     discretized
    1.96
    Activations Density 0.032%

    No Known Activations