© 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. 5295
    Prev
    Next
    INDEX
    Explanations

    numbers, automotive terminology, and units of measurement

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or specialized terms

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

    Vehicle power and specifications

    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
    cross
    -0.59
    
    -0.58
     cross
    -0.56
    WithIdentifier
    -0.53
    cros
    -0.51
    सन्दर्भ
    -0.48
    xtext
    -0.48
     Cross
    -0.48
    Cross
    -0.48
     ACTS
    -0.47
    POSITIVE LOGITS
     >=",
    0.60
    mybatisplus
    0.59
    UnusedPrivate
    0.57
    EDEFAULT
    0.55
    Enllaces
    0.54
    UrlResolution
    0.53
    rungsseite
    0.52
    ramid
    0.51
    Comté
    0.50
    ExtendWith
    0.49
    Activations Density 1.484%

    No Known Activations