© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13739
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are titles of something

    oai_token-act-pair · gemini-2.0-flash

    artistic works

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    roek
    -0.42
    ju
    -0.40
    addGroup
    -0.40
     group
    -0.37
     truc
    -0.36
    j
    -0.36
    Gemeinsame
    -0.36
    坊
    -0.35
     '/'
    -0.35
    om
    -0.35
    POSITIVE LOGITS
     pinulongan
    0.93
    __':
    0.90
    __":
    0.84
    httphttps
    0.74
    SEGUIR
    0.73
     resourceCulture
    0.71
    UIControlState
    0.69
     gainera
    0.69
    disfraz
    0.68
    böz
    0.68
    Activations Density 10.009%

    No Known Activations