© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12530
    Prev
    Next
    INDEX
    Explanations

    text describing a character's transformation or powers

    oai_token-act-pair · gemini-2.0-flash

    personal

    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
    slidesPer
    -0.60
     Wikispecies
    -0.56
     Uranus
    -0.54
    LEncoder
    -0.54
     Laat
    -0.54
    SequentialGroup
    -0.52
     Byzantium
    -0.52
    itiés
    -0.51
     forehead
    -0.51
     OpenStreetMap
    -0.51
    POSITIVE LOGITS
    Bakgrunnsstoff
    0.53
    $_['
    0.52
    enumi
    0.52
    Παραπομπές
    0.52
    Erreferentziak
    0.52
    rinfo
    0.49
    miss
    0.46
    ◀
    0.46
    homonymie
    0.46
    enumii
    0.46
    Activations Density 4.952%

    No Known Activations