© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6659
    Prev
    Next
    INDEX
    Explanations

    passages related to credit scores and insurance costs

    oai_token-act-pair · gemini-2.0-flash

    credit scores

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ResponseWriter
    -0.54
    Rhestr
    -0.50
    makeText
    -0.49
     kennis
    -0.49
    InstanceState
    -0.48
     doPost
    -0.48
     ActivatedRoute
    -0.47
    didSet
    -0.47
     taal
    -0.47
    دانشنامهٔ
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.73
    mybatisplus
    0.71
     saites
    0.60
     initComponents
    0.57
    Expose
    0.53
    siębior
    0.52
     ExecuteAsync
    0.52
     fieldNum
    0.51
    -------
    0.50
     "..\..\
    0.49
    Activations Density 1.321%

    No Known Activations