© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14693
    Prev
    Next
    INDEX
    Explanations

    code or configuration file-related tokens

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Personendaten
    -0.77
    AddHtmlAttribute
    -0.71
    nezeu
    -0.58
     utafitiHapana
    -0.56
     تضيفلها
    -0.54
    OGND
    -0.51
    NameInMap
    -0.51
    IsContent
    -0.50
    ellige
    -0.50
     babys
    -0.50
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.48
    DaoImpl
    0.46
    PDIR
    0.43
     SqlCommand
    0.41
    dk
    0.40
    md
    0.38
    mbg
    0.38
    dl
    0.38
    QRect
    0.38
    TTF
    0.37
    Activations Density 20.857%

    No Known Activations