© 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. 3172
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and excitement, especially related to games and online content.

    oai_token-act-pair · gemini-2.0-flash

    positive sentiment

    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
    RenderAtEndOf
    -0.64
    WebControls
    -0.63
     الحره
    -0.60
    transQ
    -0.59
     resourceCulture
    -0.56
    Gemeinden
    -0.55
    SourceChecksum
    -0.54
    خصة
    -0.54
    сылкі
    -0.52
    spesies
    -0.51
    POSITIVE LOGITS
    ang
    0.71
     kaarangay
    0.63
     EconPapers
    0.52
     InputDecoration
    0.50
    gud
    0.50
     nudo
    0.49
    мум
    0.48
    ANG
    0.47
    batore
    0.45
    idos
    0.45
    Activations Density 3.106%

    No Known Activations