© 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. 8804
    Prev
    Next
    INDEX
    Explanations

    mentions of concrete and metal materials, and the business manufacturing them.

    oai_token-act-pair · gemini-2.0-flash

    terms related to concrete

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

    concrete mix

    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
     viewType
    -0.63
    WritableDatabase
    -0.55
     trö
    -0.54
    dflare
    -0.53
    XmlAccessType
    -0.52
    nships
    -0.52
     postale
    -0.51
     héri
    -0.51
     uphol
    -0.50
     commerciaux
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.67
     concrete
    0.66
     mix
    0.62
     Mix
    0.59
    rete
    0.58
     ready
    0.57
     EconPapers
    0.56
     re
    0.55
     ModelExpression
    0.55
    retes
    0.54
    Activations Density 1.554%

    No Known Activations