© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13608
    Prev
    Next
    INDEX
    Explanations

    single uppercase letters

    oai_token-act-pair · gemini-2.0-flash

    names or identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Internet posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    IntoConstraints
    -0.83
    bootstrapcdn
    -0.68
    CloseOperation
    -0.66
    ersdorf
    -0.65
    Abit
    -0.65
    发表于
    -0.62
     gepubliceerd
    -0.62
    styleType
    -0.61
    WebVitals
    -0.61
    httphttps
    -0.60
    POSITIVE LOGITS
    حياتها
    0.45
    gi
    0.43
    Neden
    0.40
    joi
    0.40
     eingesch
    0.40
    size
    0.39
    getItemId
    0.37
     што
    0.37
     MSW
    0.36
    rs
    0.36
    Activations Density 0.498%

    No Known Activations