© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4986
    Prev
    Next
    INDEX
    Explanations

    measurements, especially multiples indicated with "x" or symbols related to multiplication, and some words relating to chickens

    oai_token-act-pair · gemini-2.0-flash

    Mathematical/scientific and medium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     nakalista
    -0.63
    peutic
    -0.47
    MMdd
    -0.45
    jours
    -0.45
     internetowa
    -0.44
    olucion
    -0.44
     onData
    -0.44
    unov
    -0.44
    Всего
    -0.44
    ändern
    -0.44
    POSITIVE LOGITS
    URLException
    0.73
    GEBURTSDATUM
    0.66
    StoryboardSegue
    0.66
    󠁢
    0.65
    ThroughAttribute
    0.62
    іга
    0.61
     propOrder
    0.61
    __':
    0.60
    uyasha
    0.59
     Privy
    0.59
    Activations Density 1.103%

    No Known Activations