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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2982
    Prev
    Next
    INDEX
    Explanations

    phrases like "I've ever" or "you've ever" and superlatives

    oai_token-act-pair · gemini-2.0-flash

    past event descriptions

    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
    AndroidJUnit
    -0.81
     initComponents
    -0.70
    DeleteBehavior
    -0.69
    CreateMap
    -0.66
     itſelf
    -0.65
    MessageTagHelper
    -0.63
    PyExc
    -0.63
     Superhost
    -0.63
    complexContent
    -0.62
     EClass
    -0.62
    POSITIVE LOGITS
    fhir
    0.54
    addGap
    0.53
    userdetails
    0.52
    gatsby
    0.51
    BRL
    0.46
     et
    0.45
     enca
    0.45
     jad
    0.44
    ecake
    0.44
    GENERATED
    0.44
    Activations Density 1.475%

    No Known Activations