© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5155
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to vehicle mechanical systems and engineering, especially cars and aircraft

    oai_token-act-pair · gemini-2.0-flash

    words related to engines

    np_token-act-pair-logits · gpt-4o-mini

    engine and motor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RegistryLite
    -0.58
    tagHelperRunner
    -0.58
     fermés
    -0.56
     виправивши
    -0.56
    脚注の使い方
    -0.53
     récents
    -0.52
    RegressionTest
    -0.52
     kepad
    -0.52
    anskje
    -0.51
    adə
    -0.51
    POSITIVE LOGITS
     engine
    1.18
     engines
    1.09
     Engine
    1.02
    engine
    1.00
     Engines
    0.93
     ENGINE
    0.89
    engines
    0.88
    Engine
    0.86
     motor
    0.86
     motors
    0.82
    Activations Density 1.233%

    No Known Activations