© 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. 7678
    Prev
    Next
    INDEX
    Explanations

    the word "listed", sometimes in conjunction with words like "entities", "store", or "reports"

    oai_token-act-pair · gemini-2.0-flash

    listed

    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
     
    -0.97
     just
    -0.88
     in
    -0.84
     on
    -0.78
     of
    -0.74
     the
    -0.74
     N
    -0.74
     autorytatywna
    -0.71
     so
    -0.69
     ‘
    -0.68
    POSITIVE LOGITS
     Anſ
    1.26
     Monfieur
    1.23
     Houſe
    1.20
     itſelf
    1.17
     Reſ
    1.16
     Diſ
    1.16
     themſelves
    1.16
     myſelf
    1.15
     Theſe
    1.13
     pleaſure
    1.13
    Activations Density 1.266%

    No Known Activations