© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9462
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business relationships, contracts and customer support

    oai_token-act-pair · gemini-2.0-flash

    technical specifications or standards

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

    business and legal procedures

    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
     Shakspeare
    -0.91
     itſelf
    -0.87
     myſelf
    -0.84
     Diſ
    -0.81
     ſever
    -0.81
    PYX
    -0.80
     pleaſure
    -0.79
     auffi
    -0.77
     raiſ
    -0.77
     leſs
    -0.76
    POSITIVE LOGITS
     <=",
    0.45
    INN
    0.39
     standar
    0.39
    BagLayout
    0.38
     kom
    0.37
     
    0.36
     T
    0.36
     standard
    0.36
     In
    0.35
    ñal
    0.35
    Activations Density 2.974%

    No Known Activations