© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12791
    Prev
    Next
    INDEX
    Explanations

    content about email and network servers, DNS, and related configurations

    oai_token-act-pair · gemini-2.0-flash

    Email and SMTP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.65
    Referències
    -0.53
    ertale
    -0.49
    jaz
    -0.47
     transitions
    -0.46
     consultato
    -0.46
    `${
    -0.45
    don
    -0.45
     Don
    -0.45
    GraphicsUnit
    -0.44
    POSITIVE LOGITS
     iprot
    0.73
    bootstrapcdn
    0.70
    webElementXpaths
    0.63
    .*")]
    0.63
    aarrggbb
    0.61
     propOrder
    0.60
     rospy
    0.60
    PMailer
    0.60
    IUrlHelper
    0.59
    ConstraintMaker
    0.59
    Activations Density 0.848%

    No Known Activations