© 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-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4849
    Prev
    Next
    INDEX
    Explanations

    LaTeX and C code

    oai_token-act-pair · gemini-2.0-flash

    WT or WR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     w
    -0.86
     WH
    -0.84
    wh
    -0.77
     wh
    -0.77
    WR
    -0.76
    WF
    -0.76
     Wi
    -0.72
     W
    -0.72
     WC
    -0.71
    WH
    -0.70
    POSITIVE LOGITS
    ьаж
    0.72
    illots
    0.70
    Diwedd
    0.69
     '\\;'
    0.68
    endpush
    0.66
    rungsseite
    0.66
     дописавши
    0.63
     autorytatywna
    0.62
     betweenstory
    0.61
     vPvB
    0.61
    Activations Density 2.910%

    No Known Activations