© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13457
    Prev
    Next
    INDEX
    Explanations

    words related to television and movie production

    oai_token-act-pair · gemini-2.0-flash

    show

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     evit
    -0.50
     chóng
    -0.48
     виправивши
    -0.47
     denser
    -0.46
    ніципа
    -0.46
     marion
    -0.45
     prou
    -0.43
    CHILD
    -0.43
    discovery
    -0.43
     Infan
    -0.43
    POSITIVE LOGITS
    ]")]
    0.73
    AndEndTag
    0.63
    avadoc
    0.62
     CURIAM
    0.60
    InjectAttribute
    0.59
    LookAnd
    0.58
    principalColumn
    0.57
    ReusableCell
    0.57
    Javadoc
    0.57
    <bos>
    0.57
    Activations Density 1.629%

    No Known Activations