© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10267
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "poem" or "poetry".

    oai_token-act-pair · gemini-2.0-flash

    poem

    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
     
    -1.10
      
    -1.02
     The
    -0.93
     I
    -0.92
     It
    -0.92
     A
    -0.89
    <eos>
    -0.81
     the
    -0.81
     We
    -0.80
     To
    -0.77
    POSITIVE LOGITS
     ―――――
    1.30
     photolibrary
    1.23
     Efq
    1.19
     crdi
    1.18
     auffi
    1.13
     ་་
    1.12
     ſind
    1.11
     $_"
    1.10
     doubtnut
    1.09
     autorytatywna
    1.08
    Activations Density 1.328%

    No Known Activations