© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3127
    Prev
    Next
    INDEX
    Explanations

    positive descriptors and superlatives

    oai_token-act-pair · gemini-2.0-flash

    a/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     referenties
    -0.73
     CreateTagHelper
    -0.63
     initComponents
    -0.63
    tvguidetime
    -0.61
     متعلقه
    -0.61
    CONSIN
    -0.60
    GEBURTSDATUM
    -0.57
     okuyayım
    -0.57
    存于互联网档案馆
    -0.57
    onnaise
    -0.56
    POSITIVE LOGITS
    AxisAlignment
    0.57
    //
    0.51
     remp
    0.46
     vectorielle
    0.45
    houses
    0.44
     GreatSchools
    0.43
     ChromeDriver
    0.42
    MDL
    0.42
     suprême
    0.41
    GoogleApiClient
    0.41
    Activations Density 2.197%

    No Known Activations