© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12383
    Prev
    Next
    INDEX
    Explanations

    strings of numbers and special characters that might represent URLs or DOIs

    oai_token-act-pair · gemini-2.0-flash

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    postmedia
    -0.47
    mozilla
    -0.46
     raised
    -0.44
    ApiModel
    -0.43
    Външни
    -0.41
     tartalomajánló
    -0.41
     أعلام
    -0.40
     createState
    -0.39
    raised
    -0.39
    Doh
    -0.39
    POSITIVE LOGITS
    webElementXpaths
    0.82
    AddTagHelper
    0.81
    principalColumn
    0.71
     CreateTagHelper
    0.67
    ConstraintMaker
    0.66
    ]--;
    0.63
     Paglinawan
    0.63
    ftagPool
    0.62
     nahilalakip
    0.61
    UnitTesting
    0.60
    Activations Density 0.262%

    No Known Activations