© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9695
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "one of the" or "the"

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     }}"></
    -0.47
     Başkanı
    -0.41
    mannian
    -0.40
    man
    -0.39
    iner
    -0.38
     person
    -0.37
     Allein
    -0.37
    智
    -0.36
    le
    -0.36
     pessoa
    -0.35
    POSITIVE LOGITS
     most
    0.98
    most
    0.79
     MOST
    0.76
     moſt
    0.75
    دانشنامهٔ
    0.73
    Chú
    0.71
     Most
    0.69
    AndEndTag
    0.69
     domestiques
    0.68
     poveznice
    0.67
    Activations Density 2.109%

    No Known Activations