© 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. 3515
    Prev
    Next
    INDEX
    Explanations

    words related to dates, locations, and voyages

    oai_token-act-pair · gemini-2.0-flash

    Ships and travel locations

    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
    انيف
    -0.57
    istoitu
    -0.57
    はじめに
    -0.54
    WEBPACK
    -0.52
    UnusedPrivate
    -0.50
    VIAF
    -0.49
    ManagedBean
    -0.48
    ip
    -0.48
    vrons
    -0.47
    сылкі
    -0.47
    POSITIVE LOGITS
    rrggbb
    0.60
    σθαι
    0.60
     utafitiHapana
    0.54
    hynch
    0.53
    Припев
    0.53
    **********/
    0.52
    drunk
    0.49
    những
    0.48
     مصرى
    0.48
     newArr
    0.47
    Activations Density 1.447%

    No Known Activations