© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2972
    Prev
    Next
    INDEX
    Explanations

    snippets of mathematical or scientific text

    oai_token-act-pair · gemini-2.0-flash

    academic writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Monfieur
    -0.79
     myſelf
    -0.77
    CPtr
    -0.77
    دانشنامهٔ
    -0.77
    日閲覧
    -0.76
    ValueGeneration
    -0.73
     Jefus
    -0.73
    Jeografia
    -0.73
     uſed
    -0.73
    ItemLayout
    -0.72
    POSITIVE LOGITS
     com
    0.47
    ViewFeatures
    0.45
     ge
    0.39
    бил
    0.39
    ANA
    0.38
    ragamo
    0.38
    resas
    0.36
     Ge
    0.36
    šil
    0.36
    azin
    0.36
    Activations Density 9.782%

    No Known Activations