© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4967
    Prev
    Next
    INDEX
    Explanations

    words used to express qualifications, conditions, or uncertainty.

    oai_token-act-pair · gemini-2.0-flash

    Technical passages

    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
     speech
    -1.62
     speak
    -1.59
     language
    -1.59
     Speech
    -1.48
     Language
    -1.45
    speak
    -1.44
     Speak
    -1.41
     sprach
    -1.39
     speaking
    -1.38
     spoken
    -1.38
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    nocześnie
    0.54
    medriver
    0.53
     chaus
    0.52
    colgroup
    0.50
    蚪
    0.47
    XtraGrid
    0.47
     dbg
    0.47
     actionMode
    0.46
    ArgsConstructor
    0.45
    Activations Density 2.158%

    No Known Activations