© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8100
    Prev
    Next
    INDEX
    Explanations

    the word "recall" and related words

    oai_token-act-pair · gemini-2.0-flash

    recall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     autorytatywna
    -1.70
     CreateTagHelper
    -1.49
     '\\;'
    -1.47
    Datuak
    -1.42
     تانيه
    -1.38
     Audiodateien
    -1.36
    InjectAttribute
    -1.36
    GraphicsUnit
    -1.34
     للمعارف
    -1.33
    addCriterion
    -1.32
    POSITIVE LOGITS
     
    0.84
     a
    0.79
     in
    0.78
    ,
    0.75
    je
    0.73
    in
    0.73
     –
    0.72
    an
    0.71
     two
    0.71
     (
    0.70
    Activations Density 0.342%

    No Known Activations