© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10365
    Prev
    Next
    INDEX
    Explanations

    words related to modifying data fields

    oai_token-act-pair · gemini-2.0-flash

    technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    StructEnd
    -0.79
     Agamemnon
    -0.62
     snippetHide
    -0.62
    CppCodeGen
    -0.59
    StoryboardSegue
    -0.55
     onBind
    -0.54
     INTERESAR
    -0.54
    󠁿
    -0.54
     stoneware
    -0.53
     itſelf
    -0.53
    POSITIVE LOGITS
    Bibliograf
    0.56
    ﷺ
    0.52
    featureID
    0.52
    parseFrom
    0.51
    AccessorTable
    0.49
    Portale
    0.47
     forms
    0.47
     report
    0.46
     Alford
    0.45
    BeanFactory
    0.45
    Activations Density 10.440%

    No Known Activations