© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8973
    Prev
    Next
    INDEX
    Explanations

    words containing "human" or ending in "readable"

    oai_token-act-pair · gemini-2.0-flash

    Human subjects research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    OGND
    -0.99
    RTEE
    -0.75
    principalColumn
    -0.72
    ########.
    -0.70
    Slf
    -0.69
     extradition
    -0.69
    bewerken
    -0.68
     noses
    -0.68
    الإنجليزية
    -0.67
     Exactos
    -0.67
    POSITIVE LOGITS
    reactstrap
    0.62
    aughey
    0.50
    endphp
    0.50
    <bos>
    0.48
    раздо
    0.44
     geval
    0.44
     برانيه
    0.43
     realize
    0.43
    liferay
    0.42
    About
    0.41
    Activations Density 0.539%

    No Known Activations