© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4733
    Prev
    Next
    INDEX
    Explanations

    common words with high frequency, especially quantifiers and prepositions

    oai_token-act-pair · gemini-2.0-flash

    all or most

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    AndEndTag
    -1.33
    ValueStyle
    -1.05
    sizeCache
    -0.93
    WriteTagHelper
    -0.90
    tvguidetime
    -0.90
     autorytatywna
    -0.89
    principalColumn
    -0.88
    MLLoader
    -0.88
    AnimationsModule
    -0.85
    WebElementEntity
    -0.84
    POSITIVE LOGITS
     other
    0.42
     strong
    0.39
     no
    0.38
    共に
    0.36
    こそ
    0.36
    other
    0.35
    ary
    0.35
    ともに
    0.34
    よかった
    0.34
    pre
    0.34
    Activations Density 5.479%

    No Known Activations