© 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. 1968
    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
    an
    3.13
    д
    2.84
    ers
    2.75
    ি
    2.74
    ين
    2.71
    i
    2.53
    י
    2.41
    ில்
    2.41
    ان
    2.36
    am
    2.35
    POSITIVE LOGITS
    ѕ
    2.47
     vậy
    2.30
     siglas
    2.22
    𝖘
    2.16
    ис
    2.14
     особенностей
    2.13
    𝚜
    2.11
     tráfico
    2.09
    ContentLoaded
    2.09
    𝐬
    2.07
    Activations Density 0.241%

    No Known Activations