© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8878
    Prev
    Next
    INDEX
    Explanations

    a mix of generally positive and negative terms, technical terms related to science and business models

    oai_token-act-pair · gemini-2.0-flash

    ork/Org

    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
     noDo
    -0.68
    ReusableCell
    -0.60
    SourceChecksum
    -0.59
    AccessFile
    -0.56
    vre
    -0.56
    ngOn
    -0.52
    новниш
    -0.52
     оригіналу
    -0.51
    bre
    -0.50
    }{*}{
    -0.49
    POSITIVE LOGITS
    ork
    0.75
     Ork
    0.72
    org
    0.70
     ORG
    0.69
     org
    0.68
     Ord
    0.67
    orb
    0.66
    ardı
    0.65
    ordi
    0.65
    ordu
    0.65
    Activations Density 3.187%

    No Known Activations