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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10984
    Prev
    Next
    INDEX
    Explanations

    words/phrases that convey a strong negative sentiment or complaint about something

    oai_token-act-pair · gemini-2.0-flash

    jam

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     wijze
    -0.60
     ketahui
    -0.59
    angles
    -0.57
     istruzioni
    -0.57
    Datuak
    -0.51
     symmetries
    -0.51
    cauciones
    -0.51
    attempts
    -0.51
    geometry
    -0.50
    tudes
    -0.50
    POSITIVE LOGITS
     noDo
    0.72
    WebVitals
    0.57
    WriteTagHelper
    0.56
    ArgsConstructor
    0.54
    >");
    0.52
     onCancelled
    0.51
    MessageTagHelper
    0.51
     بيها
    0.51
    EDEFAULT
    0.49
    complexContent
    0.48
    Activations Density 19.041%

    No Known Activations