© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10123
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with academic research studies.

    oai_token-act-pair · gemini-2.0-flash

    studies and properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Paglinawan
    -0.54
    ensores
    -0.53
    indd
    -0.53
    saraba
    -0.52
     God
    -0.50
    amigos
    -0.49
    ThroughAttribute
    -0.49
    rore
    -0.49
    timas
    -0.48
    osoma
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.65
     récomp
    0.59
     élu
    0.55
     elettrico
    0.54
    ⓧ
    0.54
    الدراسه
    0.53
     réguli
    0.53
     électriques
    0.53
     Wiktionnaire
    0.52
     Allociné
    0.52
    Activations Density 7.467%

    No Known Activations