© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12089
    Prev
    Next
    INDEX
    Explanations

    math notation

    oai_token-act-pair · gemini-2.0-flash

    code or mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     مشين
    -0.93
    IUrlHelper
    -0.79
     disambiguazione
    -0.77
    ））
    -0.71
    "])
    -0.70
    "));
    -0.69
    ########.
    -0.69
    istocene
    -0.68
     useHistory
    -0.68
    "]).
    -0.68
    POSITIVE LOGITS
    moduleId
    0.36
    config
    0.36
    PasswordEncoder
    0.36
     geral
    0.35
    IBOutlet
    0.35
     hyö
    0.35
     efisien
    0.35
    =";
    0.35
     umumnya
    0.35
    fromLTRB
    0.35
    Activations Density 0.806%

    No Known Activations