© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3884
    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
    us
    2.40
    𝐬
    2.36
    𝖚
    2.35
    ה
    2.12
    𝚔
    2.08
    িন
    2.06
    ர்
    2.04
     signification
    2.04
    िडी
    2.04
    くれる
    2.03
    POSITIVE LOGITS
    \,
    2.76
    \%
    2.45
     América
    2.43
    😍😍
    2.23
    ittal
    2.14
     त्यौहार
    2.13
    憔
    2.10
    Chúc
    2.10
     adequada
    2.09
     tiros
    2.07
    Activations Density 0.004%

    No Known Activations