© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9430
    Prev
    Next
    INDEX
    Explanations

    mentions of rankings in sports or other competitive events

    oai_token-act-pair · gemini-2.0-flash

    Rankings and finishing positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    BeginContext
    -0.96
     betweenstory
    -0.74
    bootstrapcdn
    -0.71
    Personendaten
    -0.69
     iprot
    -0.69
    ValueStyle
    -0.68
    Datuak
    -0.68
     мәкал
    -0.68
    kloped
    -0.66
    mergeFrom
    -0.66
    POSITIVE LOGITS
     PSV
    0.58
     tuta
    0.43
     Upload
    0.42
     Turnpike
    0.42
    isSuccessful
    0.42
     Arma
    0.42
    ponible
    0.41
     couvre
    0.40
     Vial
    0.40
    gius
    0.40
    Activations Density 15.624%

    No Known Activations