© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9153
    Prev
    Next
    INDEX
    Explanations

    words that introduce questions or thought processes and connect ideas

    oai_token-act-pair · gemini-2.0-flash

    how

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     cuantos
    -0.48
    Few
    -0.44
     Few
    -0.44
     particulières
    -0.42
     Them
    -0.41
    few
    -0.40
     particulière
    -0.40
     poucos
    -0.40
     preuves
    -0.39
    strijden
    -0.38
    POSITIVE LOGITS
     there
    0.76
    FieldBuilder
    0.71
    ContentAsync
    0.70
     تضيفلها
    0.68
    AndEndTag
    0.68
    errHandler
    0.68
     Anſ
    0.66
     saites
    0.66
    IInterface
    0.66
    UnusedPrivate
    0.65
    Activations Density 7.204%

    No Known Activations