Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14662
    Prev
    Next
    INDEX
    Explanations

    mentions of an individual solving a different person's problems

    oai_token-act-pair · gemini-2.0-flash

    Acts of communication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CreateTagHelper
    -0.79
    хьтан
    -0.76
     nahilalakip
    -0.72
    #+#
    -0.70
    WebVitals
    -0.69
    Hentet
    -0.65
    waitKey
    -0.61
     насељу
    -0.60
    InjectAttribute
    -0.60
     kasarigan
    -0.59
    POSITIVE LOGITS
     offered
    0.55
     taught
    0.55
     treated
    0.54
     communicated
    0.52
     accommodated
    0.51
    taught
    0.51
     coached
    0.50
     introduced
    0.50
     hosted
    0.49
     addressed
    0.49
    Activations Density 1.182%

    No Known Activations