© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15079
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to familial relationships and feeling at home

    oai_token-act-pair · gemini-2.0-flash

    belonging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     propOrder
    -0.92
     nahilalakip
    -0.85
    ագրություններ
    -0.78
    oa̍t
    -0.77
    Cyfeiriadau
    -0.74
     Italijanski
    -0.73
     ويكيپيديا
    -0.72
     سكانية
    -0.71
    AndEndTag
    -0.71
    saraba
    -0.70
    POSITIVE LOGITS
     институт
    0.44
    گو
    0.44
     reager
    0.43
    es
    0.43
     tuin
    0.41
    og
    0.41
     durumda
    0.41
    .
    0.41
    ol
    0.41
    um
    0.41
    Activations Density 0.996%

    No Known Activations