© 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. 8196
    Prev
    Next
    INDEX
    Explanations

    the conjunction 'and,' the word 'foundation,' numbers written as digits, and the words 'profit' and 'organization'

    oai_token-act-pair · gemini-2.0-flash

    nonprofit organizations

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

    nonprofit organization

    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
    帖最后由
    -0.85
    niająca
    -0.62
    AnchorTagHelper
    -0.60
    ỡng
    -0.59
    >{@
    -0.59
    íncia
    -0.56
    dolu
    -0.54
    IsContent
    -0.53
    featureID
    -0.52
     يتيمه
    -0.51
    POSITIVE LOGITS
     not
    0.66
     nonprofit
    0.61
     corps
    0.59
     non
    0.58
     panel
    0.57
    not
    0.57
     organization
    0.57
    Portail
    0.56
    Spoljašnje
    0.55
     international
    0.54
    Activations Density 1.399%

    No Known Activations