© 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. 15284
    Prev
    Next
    INDEX
    Explanations

    proper nouns of films and shows, especially ones with a focus on marginalized communities.

    oai_token-act-pair · gemini-2.0-flash

    families or court cases

    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
    出版年
    -0.72
     AssemblyProduct
    -0.62
    protoimpl
    -0.58
     InputDecoration
    -0.57
    AllAfrica
    -0.55
    mybatisplus
    -0.54
    Източници
    -0.54
     kasarigan
    -0.54
    jsdelivr
    -0.53
    VolleyError
    -0.52
    POSITIVE LOGITS
     funniest
    0.54
     bombas
    0.53
    PERM
    0.52
     pedigree
    0.49
    Ẳ
    0.49
     pute
    0.48
    ก
    0.46
     metav
    0.45
     Regel
    0.45
    providedIn
    0.45
    Activations Density 1.693%

    No Known Activations