© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7751
    Prev
    Next
    INDEX
    Explanations

    descriptions of a quarterback being pressured or sacked in football

    oai_token-act-pair · gemini-2.0-flash

    American football

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    UnsafeEnabled
    -0.71
    BeginContext
    -0.64
    الإنجليزية
    -0.57
    Passing
    -0.52
     Passing
    -0.51
    Földrajzportál
    -0.51
    chafft
    -0.49
     كومونز
    -0.47
     Orbital
    -0.47
    ',
    -0.47
    POSITIVE LOGITS
    UnusedPrivate
    0.63
    oporosis
    0.57
    fromnode
    0.53
    Personendaten
    0.50
    Kilder
    0.49
     pocket
    0.49
    pocket
    0.47
    DeleteMapping
    0.47
    stdint
    0.47
     disparu
    0.46
    Activations Density 4.470%

    No Known Activations