© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 487
    Prev
    Next
    INDEX
    Explanations

    terms related to email management and interfaces, including spam and interface usage within coding

    oai_token-act-pair · gemini-2.0-flash

    email

    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
    ApiOperation
    -0.53
    featureID
    -0.52
    发表于
    -0.52
    /******/
    -0.50
    XmlAccessType
    -0.50
    webElementXpaths
    -0.48
    Viited
    -0.48
     bezeichneter
    -0.48
    сылкі
    -0.46
    CloseOperation
    -0.45
    POSITIVE LOGITS
     Pristup
    0.58
     العام
    0.55
     Abstr
    0.53
    ertale
    0.52
    ibase
    0.51
    antart
    0.50
     rentrée
    0.50
    Referències
    0.50
    AllowUser
    0.50
    trar
    0.50
    Activations Density 48.661%

    No Known Activations