© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13010
    Prev
    Next
    INDEX
    Explanations

    words indicating scientific research and publications

    oai_token-act-pair · gemini-2.0-flash

    attention/interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    UserScript
    -1.04
     myſelf
    -0.98
    StoryboardSegue
    -0.90
     Weyl
    -0.88
    esModule
    -0.85
     Wikimedijinoj
    -0.84
    TypedDataSet
    -0.84
    AndEndTag
    -0.83
     Италијани
    -0.83
     ſind
    -0.83
    POSITIVE LOGITS
     problem
    0.41
     im
    0.40
    までに
    0.38
    COMMUNITY
    0.37
    Community
    0.36
    了吗
    0.36
     Er
    0.35
     komunitas
    0.35
     [
    0.34
     plan
    0.34
    Activations Density 3.376%

    No Known Activations