© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12023
    Prev
    Next
    INDEX
    Explanations

    the word "hang" followed by prepositions like "out", "up", "on", or "onto"

    oai_token-act-pair · gemini-2.0-flash

    hang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     hangs
    -1.07
     hang
    -1.02
     hanging
    -0.99
     hung
    -0.98
    hanging
    -0.96
    Hanging
    -0.95
     Hang
    -0.93
     suspendu
    -0.91
     hanged
    -0.91
     Hanging
    -0.90
    POSITIVE LOGITS
     bParam
    0.56
    complexType
    0.54
    pielt
    0.54
    GIVEREF
    0.52
    PageIndex
    0.51
     мәгълү
    0.50
    tagext
    0.49
    ätten
    0.49
    subsubsection
    0.47
    alsch
    0.47
    Activations Density 2.688%

    No Known Activations