© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15504
    Prev
    Next
    INDEX
    Explanations

    words related to professional occupations and positions, especially pertaining to legal and historical contexts

    oai_token-act-pair · gemini-2.0-flash

    succession or legal respondents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     theory
    -0.54
     theorems
    -0.53
     Theorems
    -0.52
    theory
    -0.52
    tocin
    -0.51
    TagMode
    -0.50
     respectively
    -0.50
    staaten
    -0.48
    setDo
    -0.48
    seye
    -0.47
    POSITIVE LOGITS
    ItemBackground
    0.77
    rungsseite
    0.67
     continúas
    0.63
    SharedDtor
    0.62
    ConstraintMaker
    0.59
    oa̍t
    0.59
    GenerationType
    0.59
    بوابة
    0.58
    hoeddwyd
    0.57
    曖昧さ回避
    0.57
    Activations Density 2.194%

    No Known Activations