© 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. 14108
    Prev
    Next
    INDEX
    Explanations

    text about railways and locations beginning with "Bur"

    oai_token-act-pair · gemini-2.0-flash

    proper nouns related to locations or names

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

    Wales and railways

    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
    MigrationBuilder
    -0.74
    +#+
    -0.70
     transfieras
    -0.65
     estimés
    -0.64
    findpost
    -0.64
     Obrador
    -0.55
    IUrlHelper
    -0.55
    mybatisplus
    -0.55
    arena
    -0.54
    sidemargin
    -0.54
    POSITIVE LOGITS
    djangoproject
    0.55
     Egli
    0.49
    Cata
    0.49
    andinavia
    0.48
     Cata
    0.48
    cuidado
    0.47
     boxed
    0.46
    epresidente
    0.46
     pê
    0.45
    andinavian
    0.43
    Activations Density 0.210%

    No Known Activations