© 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. 2389
    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
    appropri
    2.66
    𝐝
    2.63
    𝐅
    2.30
    𝐫
    2.30
    pageNum
    2.27
     تکلیف
    2.25
    vf
    2.22
    𝐧
    2.21
     unquestion
    2.18
     diced
    2.18
    POSITIVE LOGITS
    bies
    2.40
     hề
    2.38
    etheless
    2.32
    t
    2.29
    వ్వ
    2.28
    ্সের
    2.22
    锈钢
    2.20
     adanya
    2.19
    д
    2.14
    pygame
    2.12
    Activations Density 0.363%

    No Known Activations