© 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. 13701
    Prev
    Next
    INDEX
    Explanations

    mentions of politics, health care, science, disagreement/conflict, file table management, authority and personal history or study details.

    oai_token-act-pair · gemini-2.0-flash

    "or" in different languages

    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
     ་་
    -0.73
     mxArray
    -0.69
     ―――――
    -0.68
    TagMode
    -0.67
     myſelf
    -0.65
     raiſ
    -0.65
     ſind
    -0.64
    ſelf
    -0.63
     Ril
    -0.62
     imago
    -0.62
    POSITIVE LOGITS
     or
    3.02
     или
    2.09
     atau
    1.89
    或
    1.83
     eller
    1.81
     oder
    1.64
    หรือ
    1.64
    或者
    1.63
     hoặc
    1.61
     یا
    1.60
    Activations Density 12.505%

    No Known Activations