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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6300
    Prev
    Next
    INDEX
    Explanations

    colons followed by some information and then "to" and "from" designations.

    oai_token-act-pair · gemini-2.0-flash

    colon character

    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
    '
    -0.84
    (
    -0.71
    ’
    -0.64
    -
    -0.63
    S
    -0.54
    ↵↵
    -0.54
    V
    -0.54
    1
    -0.53
    A
    -0.53
    N
    -0.53
    POSITIVE LOGITS
     EconPapers
    1.23
    Autoritní
    1.13
    :✨
    1.12
     autorytatywna
    1.09
    Personensuche
    1.04
    ScopeManager
    0.96
    enumi
    0.95
    Personendaten
    0.95
    Hentet
    0.95
    AnchorStyles
    0.93
    Activations Density 8.413%

    No Known Activations