© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10495
    Prev
    Next
    INDEX
    Explanations

    words related to stages of development in insects, diseases, coding, testing, and school

    oai_token-act-pair · gemini-2.0-flash

    insect development stages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     nakalista
    -0.93
    TagMode
    -0.91
    IntoConstraints
    -0.84
     betweenstory
    -0.84
    AnchorStyles
    -0.83
     wireType
    -0.80
    Autoritní
    -0.78
     GenerationType
    -0.77
     AssemblyCompany
    -0.77
    tvguidetime
    -0.76
    POSITIVE LOGITS
    til
    0.43
     Til
    0.43
    열
    0.41
    Configurer
    0.38
    rijk
    0.37
     left
    0.36
    forRoot
    0.35
    ことがあります
    0.35
    <u>
    0.35
    quinas
    0.34
    Activations Density 12.735%

    No Known Activations