© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9131
    Prev
    Next
    INDEX
    Explanations

    sections of code or program-like text

    oai_token-act-pair · gemini-2.0-flash

    code and technical discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ”
    -0.52
     “
    -0.50
     
    -0.46
    _
    -0.46
     ”
    -0.46
    ”.
    -0.45
    “
    -0.44
     +
    -0.44
    kup
    -0.43
    CHO
    -0.43
    POSITIVE LOGITS
    UnknownFields
    0.91
    Geplaatst
    0.88
     ſhe
    0.88
     pleaſure
    0.84
     itſelf
    0.83
    ItemBackground
    0.81
     myſelf
    0.81
     Jefus
    0.80
     againſt
    0.80
    onActivityResult
    0.80
    Activations Density 0.111%

    No Known Activations