© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1023
    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
    \{
    2.14
    _:
    2.08
    ❥
    2.07
    는
    2.04
     involution
    2.01
     instrumentality
    1.95
     poes
    1.94
    था
    1.90
    \,
    1.90
     erst
    1.89
    POSITIVE LOGITS
    ي
    3.50
    l
    3.49
    zelfde
    2.55
    ن
    2.54
    er
    2.45
    iť
    2.42
    на
    2.22
    mselves
    2.17
    lcd
    2.15
     keď
    2.14
    Activations Density 0.045%

    No Known Activations