Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 845
    Prev
    Next
    INDEX
    Explanations

    URLs

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ParallelGroup
    -0.62
    <bos>
    -0.58
    Попис
    -0.57
     gynhyrchwyd
    -0.54
    BorderFactory
    -0.52
     Waray
    -0.51
    beelding
    -0.50
    aktur
    -0.50
    :]:
    -0.49
     CreateTagHelper
    -0.49
    POSITIVE LOGITS
    enterOuterAlt
    0.60
     textStatus
    0.53
    CompleteListener
    0.53
     snippetHide
    0.51
     ſte
    0.51
    ObjectModel
    0.51
     poffe
    0.49
     ſen
    0.48
    ContentAsync
    0.48
    oids
    0.47
    Activations Density 1.763%

    No Known Activations