© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1525
    Prev
    Next
    INDEX
    Explanations

    words that relate to experiencing something, such as hearing, seeing, thinking, believing, etc.

    oai_token-act-pair · gemini-2.0-flash

    hearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     kasarigan
    -0.99
     hears
    -0.94
     listening
    -0.93
     hear
    -0.89
     hearing
    -0.85
     heard
    -0.84
     Hear
    -0.81
     listened
    -0.81
     listen
    -0.81
    kloped
    -0.80
    POSITIVE LOGITS
     by
    0.47
    fred
    0.45
     look
    0.45
    مراجع
    0.44
    segna
    0.44
    sunami
    0.44
    sø
    0.43
    ristiano
    0.42
    Segue
    0.42
    anski
    0.42
    Activations Density 38.521%

    No Known Activations