© 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. 14589
    Prev
    Next
    INDEX
    Explanations

    words starting with "Fre"

    oai_token-act-pair · gemini-2.0-flash

    fre

    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
    jboss
    -0.56
     General
    -0.54
     who
    -0.52
     Gemein
    -0.49
     ring
    -0.49
    ochond
    -0.49
     general
    -0.47
    RING
    -0.47
    ring
    -0.46
     Ren
    -0.46
    POSITIVE LOGITS
     ProtoMessage
    0.75
     تضيفلها
    0.71
     متعلقه
    0.70
     سكانية
    0.67
     transfieras
    0.66
     للاسماء
    0.65
    躇
    0.64
    цездатний
    0.64
    '}>
    0.63
    __);
    0.63
    Activations Density 0.223%

    No Known Activations