© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11199
    Prev
    Next
    INDEX
    Explanations

    java code

    oai_token-act-pair · gemini-2.0-flash

    public

    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
    InjectAttribute
    -0.50
    __":
    -0.47
     okuyayım
    -0.47
    __':
    -0.46
     bună
    -0.44
    InputTagHelper
    -0.44
    ==""){
    -0.43
    apollo
    -0.43
    XmlAccessType
    -0.43
    ViewChild
    -0.43
    POSITIVE LOGITS
     yourselves
    0.59
    TypedDataSet
    0.59
    ələ
    0.58
     FontWeight
    0.58
     bezeichneter
    0.57
    Congratulations
    0.56
     createDate
    0.54
     UIAlert
    0.53
     يتيمه
    0.53
    BeginContext
    0.53
    Activations Density 0.245%

    No Known Activations