© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6787
    Prev
    Next
    INDEX
    Explanations

    the prefix "Sin" like in "Sinister" or "sinusitis"

    oai_token-act-pair · gemini-2.0-flash

    sin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Nothing
    -1.06
     nothing
    -1.05
     anything
    -1.03
     Nothing
    -1.02
    anything
    -1.02
    Anything
    -1.00
    nothing
    -0.98
     Anything
    -0.97
     something
    -0.96
    Something
    -0.96
    POSITIVE LOGITS
    setTag
    0.46
    bir
    0.46
    rzost
    0.43
     Kauf
    0.43
    yip
    0.42
    ta
    0.41
     settlement
    0.41
    ért
    0.41
    umbuhan
    0.40
    tag
    0.40
    Activations Density 0.542%

    No Known Activations