© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11146
    Prev
    Next
    INDEX
    Explanations

    instances of legal or custodial supervision

    oai_token-act-pair · gemini-2.0-flash

    supervision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.96
     prieten
    -0.78
     skolen
    -0.76
     nemlig
    -0.73
    føl
    -0.72
     the
    -0.70
     verhalen
    -0.68
     imidlertid
    -0.68
     entrambi
    -0.66
     vechi
    -0.66
    POSITIVE LOGITS
    AndEndTag
    0.83
    NameInMap
    0.81
    ChildScrollView
    0.74
     Normdatei
    0.73
    Hochspringen
    0.69
     surla
    0.69
     useRouter
    0.68
    ContentAsync
    0.67
    AnchorStyles
    0.66
    aktery
    0.65
    Activations Density 1.386%

    No Known Activations