© 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. 538
    Prev
    Next
    INDEX
    Explanations

    parts of formatting tags or equations

    oai_token-act-pair · gemini-2.0-flash

    dep

    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
    GEBURTSDATUM
    -0.80
    Véxase
    -0.69
     Poe
    -0.65
     Riche
    -0.64
    featureID
    -0.64
     Belich
    -0.63
     Lohan
    -0.63
     disambiguazione
    -0.62
     Nellie
    -0.61
    CORBA
    -0.60
    POSITIVE LOGITS
    barrow
    0.59
     Hickory
    0.55
     Erste
    0.54
     Grenville
    0.53
     Clayton
    0.52
     Gass
    0.52
     Cohort
    0.52
     Buckley
    0.52
    erle
    0.52
     TIC
    0.51
    Activations Density 4.032%

    No Known Activations