© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2728
    Prev
    Next
    INDEX
    Explanations

    abstract phrases describing a person being grounded or anchored

    oai_token-act-pair · gemini-2.0-flash

    grounded, anchored

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     pinulongan
    -0.71
    DataAnnotations
    -0.67
     iſt
    -0.67
    riwal
    -0.65
    InputTagHelper
    -0.65
     ―――――
    -0.65
     ſche
    -0.65
     Valeria
    -0.65
     getItemCount
    -0.64
     Sigmund
    -0.64
    POSITIVE LOGITS
     anchored
    0.62
     ancor
    0.57
    anchor
    0.54
     grounded
    0.54
    anchors
    0.53
     anchoring
    0.51
     anchor
    0.51
     anchors
    0.50
     positioned
    0.49
     rooted
    0.49
    Activations Density 1.408%

    No Known Activations