© 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. 3060
    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
    𝕣
    3.38
    el
    3.09
    𝕦
    2.87
    𝕤
    2.86
    r
    2.85
    𝕨
    2.78
    𝗮
    2.75
    ب
    2.62
    拷
    2.58
    𝗿
    2.58
    POSITIVE LOGITS
    navigationItem
    3.07
     Undoubtedly
    2.86
     бле
    2.86
     embroiled
    2.78
     Sensing
    2.77
     именно
    2.74
    assertThat
    2.61
    无疑
    2.59
    śmy
    2.59
    ことにより
    2.58
    Activations Density 0.045%

    No Known Activations