© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1804
    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
    ر
    3.42
    ن
    3.11
    𝑛
    3.05
    𝑝
    2.70
    শ
    2.66
    н
    2.58
    𝑚
    2.58
    𝑎
    2.57
    𝑒
    2.53
    ्स
    2.52
    POSITIVE LOGITS
    तिरिक्त
    2.47
    剤
    2.40
    ه
    2.38
    चानक
    2.33
     demikian
    2.32
     сон
    2.25
     Именно
    2.24
    <0x80>
    2.15
    蕤
    2.14
     maturities
    2.11
    Activations Density 0.023%

    No Known Activations