© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7809
    Prev
    Next
    INDEX
    Explanations

    terms related to formal structures, organizations and places

    oai_token-act-pair · gemini-2.0-flash

    government/sports/organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nearly
    -0.52
     $
    -0.50
     I
    -0.49
     Nearly
    -0.46
     several
    -0.46
     واش
    -0.45
    UMBIA
    -0.44
     listos
    -0.44
     "
    -0.43
     Z
    -0.43
    POSITIVE LOGITS
     Efq
    1.00
     myſelf
    0.95
     Monfieur
    0.94
     ſta
    0.85
     Reſ
    0.84
    EndGlobalSection
    0.84
     purpoſe
    0.83
     Diſ
    0.83
     itſelf
    0.82
    ſelf
    0.82
    Activations Density 2.210%

    No Known Activations