© 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. 3288
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names and locations

    oai_token-act-pair · gemini-2.0-flash

    Entities

    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
    ristor
    -0.48
    ènements
    -0.48
    nextProps
    -0.45
    BagConstraints
    -0.45
     popsic
    -0.43
    ряд
    -0.43
    roach
    -0.42
    siella
    -0.42
     acidosis
    -0.40
     Lazar
    -0.40
    POSITIVE LOGITS
    findpost
    0.77
     nahilalakip
    0.76
     resourceCulture
    0.71
    Datuak
    0.67
     esternos
    0.65
     autorytatywna
    0.60
    Kanpo
    0.60
    tagHelperRunner
    0.59
    voorbeeld
    0.57
    AsUp
    0.56
    Activations Density 0.095%

    No Known Activations