© 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. 7900
    Prev
    Next
    INDEX
    Explanations

    the word "song" and related terms like "lyrics"

    oai_token-act-pair · gemini-2.0-flash

    song

    np_max-act · gemini-2.0-flash

    ▁song

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     connus
    -0.86
     énergé
    -0.81
     <=",
    -0.79
     démocr
    -0.78
     épaules
    -0.76
     dysplasia
    -0.76
     quelcon
    -0.75
     africains
    -0.75
     élas
    -0.75
     originaux
    -0.74
    POSITIVE LOGITS
     LUMP
    0.64
     [],
    0.64
     {},
    0.63
     textStatus
    0.60
    //
    0.57
    ‌ای
    0.57
    ]:
    0.56
     CCR
    0.56
    ?";
    0.56
    ſelves
    0.55
    Activations Density 2.545%

    No Known Activations