© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1993
    Prev
    Next
    INDEX
    Explanations

    instances of someone being "drawn" to something, either literally or figuratively

    oai_token-act-pair · gemini-2.0-flash

    direction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Personensuche
    -0.58
    webElementXpaths
    -0.55
    IconModule
    -0.54
    Anhalt
    -0.51
     houſe
    -0.51
    ttemberg
    -0.50
    InputTagHelper
    -0.50
    Portail
    -0.50
    kháu
    -0.50
    tania
    -0.49
    POSITIVE LOGITS
     towards
    0.82
     Towards
    0.79
     toward
    0.77
     Toward
    0.72
    towards
    0.71
    Towards
    0.67
    toward
    0.66
     kepada
    0.54
    makeText
    0.54
     unto
    0.53
    Activations Density 0.789%

    No Known Activations