© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13773
    Prev
    Next
    INDEX
    Explanations

    text from the beginning or middle of a math textbook

    oai_token-act-pair · gemini-2.0-flash

    relations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     myſelf
    -0.88
     itſelf
    -0.84
     Jefus
    -0.81
     Efq
    -0.81
     الحره
    -0.81
     $_"
    -0.77
     Theſe
    -0.77
     Monfieur
    -0.75
     Houſe
    -0.75
     whoſe
    -0.75
    POSITIVE LOGITS
     relation
    0.61
     Relation
    0.50
     R
    0.50
    relation
    0.48
     relations
    0.47
     equivalence
    0.47
     RELATION
    0.46
    wachsene
    0.45
     ir
    0.45
     par
    0.44
    Activations Density 2.408%

    No Known Activations