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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6163
    Prev
    Next
    INDEX
    Explanations

    positive descriptors of residential property and community

    oai_token-act-pair · gemini-2.0-flash

    technical programming or web-related terms

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

    real estate

    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
     tartalomajánló
    -0.67
    erals
    -0.59
    vgili
    -0.59
     ويكيپيديا
    -0.56
     estekak
    -0.54
    omiast
    -0.52
     bague
    -0.52
    ſelves
    -0.52
    ũng
    -0.51
    IntegerField
    -0.50
    POSITIVE LOGITS
    BeginContext
    0.65
     utafitiHapana
    0.57
    SequentialGroup
    0.57
     interiors
    0.54
    WebElementEntity
    0.52
    UrlResolution
    0.51
    ParallelGroup
    0.50
     nonatomic
    0.49
     оригинала
    0.49
    DoubleQuotes
    0.48
    Activations Density 1.118%

    No Known Activations