© 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. 7878
    Prev
    Next
    INDEX
    Explanations

    the word "APPRO" or similar short words with capital letters

    oai_token-act-pair · gemini-2.0-flash

    words starting with "Appro"

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

    code snippets

    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
    ValueStyle
    -0.53
     resourceCulture
    -0.50
     initComponents
    -0.47
    esez
    -0.46
     INSEE
    -0.46
    LICENSE
    -0.45
     trajets
    -0.45
    ícola
    -0.44
     cref
    -0.44
     integri
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.61
     Dernière
    0.57
    Salut
    0.51
     convite
    0.50
    :✨
    0.50
    cura
    0.50
    propTypes
    0.50
     Offisielt
    0.50
    prite
    0.50
    iettivo
    0.49
    Activations Density 1.577%

    No Known Activations