© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4069
    Prev
    Next
    INDEX
    Explanations

    words indicating position or status in a hierarchy, especially job titles and sports positions

    oai_token-act-pair · gemini-2.0-flash

    people and teams

    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
    帖最后由
    -0.72
     صوتيه
    -0.68
    WebVitals
    -0.67
    tagHelperRunner
    -0.66
    ########.
    -0.66
    <bos>
    -0.63
     unknownFields
    -0.61
     Вікі
    -0.60
    المشاركات
    -0.59
     springfox
    -0.59
    POSITIVE LOGITS
    どん
    0.60
     LCCN
    0.56
     Sosten
    0.55
    كين
    0.54
    WillAppear
    0.52
    deman
    0.52
    bildung
    0.52
     bond
    0.50
     getItemCount
    0.49
    ACION
    0.49
    Activations Density 0.631%

    No Known Activations