© 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. 3864
    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
     semn
    2.66
    ്
    2.64
     colocado
    2.49
     epinephrine
    2.47
    ป์
    2.44
    其次
    2.43
    峭
    2.42
     Lancet
    2.42
    marginLeft
    2.41
    iconductor
    2.40
    POSITIVE LOGITS
    𝐞
    3.97
    𝐢
    3.78
    𝐦
    3.78
    𝐥
    3.64
    𝐬
    3.60
    𝐡
    3.53
    𝐧
    3.42
    𝐠
    3.38
    𝐝
    3.18
    𝐯
    3.13
    Activations Density 0.056%

    No Known Activations