© 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. 3288
    Prev
    Next
    INDEX
    Explanations

    a city being referenced

    oai_token-act-pair · gemini-2.0-flash

    words related to "home"

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

    home

    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
     насељу
    -0.65
    XmlAccessType
    -0.61
    SharedDtor
    -0.58
    InputTagHelper
    -0.56
    awtextra
    -0.55
     colazione
    -0.52
    WriteTagHelper
    -0.52
    StoryboardSegue
    -0.48
    DebuggerNonUser
    -0.48
    sizeCache
    -0.48
    POSITIVE LOGITS
     home
    3.75
    home
    3.08
    Home
    2.69
     Home
    2.67
     HOME
    2.63
    HOME
    2.38
     hogar
    2.20
     homes
    2.00
     hjem
    1.94
     thuis
    1.84
    Activations Density 1.507%

    No Known Activations