© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10030
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating quantity

    oai_token-act-pair · gemini-2.0-flash

    quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ffindor
    -0.62
    richTextPanel
    -0.59
    IVEREF
    -0.59
    sidemargin
    -0.58
     &___
    -0.58
    StreetMap
    -0.58
    preventDefault
    -0.57
    󠁴
    -0.57
    webElementGuid
    -0.57
    endenza
    -0.56
    POSITIVE LOGITS
    Geplaatst
    0.51
    Portale
    0.49
    romes
    0.46
    ajo
    0.45
    volen
    0.43
    verwijspagina
    0.43
    Dichloroethane
    0.42
     Sando
    0.41
    schedulers
    0.39
     Wals
    0.39
    Activations Density 0.446%

    No Known Activations