© 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. 8056
    Prev
    Next
    INDEX
    Explanations

    proper nouns consisting of one or two syllables

    oai_token-act-pair · gemini-2.0-flash

    compound terms related to modules or classes

    np_token-act-pair-logits · gpt-4o-mini
    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
    withstanding
    -1.16
    которые
    -1.09
    foundland
    -0.96
    dawnictwo
    -0.90
    giveness
    -0.86
    tonsoft
    -0.85
    tably
    -0.83
    StreetMap
    -0.82
    oubtedly
    -0.78
    veloppement
    -0.72
    POSITIVE LOGITS
    stood
    0.85
    ulario
    0.83
    guien
    0.78
    IconModule
    0.73
    ButtonModule
    0.71
    hiculo
    0.71
    dasarkan
    0.69
    ocidad
    0.67
    здрав
    0.66
    достатки
    0.65
    Activations Density 1.191%

    No Known Activations