© 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. 12646
    Prev
    Next
    INDEX
    Explanations

    words related to railroads or to rally car racing

    oai_token-act-pair · gemini-2.0-flash

    terms related to turning or curves

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

    turns

    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
    mybatisplus
    -0.63
     RSSSF
    -0.57
    ñe
    -0.54
    êcher
    -0.53
    VIAF
    -0.52
    webElementXpaths
    -0.52
     Fleece
    -0.48
     OFDb
    -0.48
    lasm
    -0.48
     createState
    -0.47
    POSITIVE LOGITS
     turns
    0.91
     turn
    0.88
    turn
    0.83
     curve
    0.82
     turning
    0.80
    Turn
    0.79
     curves
    0.79
    curve
    0.77
     Turn
    0.77
    turns
    0.75
    Activations Density 1.678%

    No Known Activations