© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2304
    Prev
    Next
    INDEX
    Explanations

    clauses starting with "I was"

    oai_token-act-pair · gemini-2.0-flash

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     autorytatywna
    -0.81
    RegressionTest
    -0.75
    XmlAccessType
    -0.72
    RetentionPolicy
    -0.69
    SharedDtor
    -0.64
    posedge
    -0.64
     ProtoMessage
    -0.63
     protoimpl
    -0.63
    GEBURTSDATUM
    -0.61
     CreateTagHelper
    -0.60
    POSITIVE LOGITS
     Victim
    0.52
     aidé
    0.51
     Schall
    0.51
     condamné
    0.51
     connues
    0.50
     laude
    0.49
     victim
    0.49
     Abp
    0.48
     blessé
    0.48
    ikko
    0.47
    Activations Density 3.780%

    No Known Activations