© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5931
    Prev
    Next
    INDEX
    Explanations

    words that begin or end an a change of topic and/or indicate emotion.

    oai_token-act-pair · gemini-2.0-flash

    anyway

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     or
    -0.75
     her
    -0.70
     same
    -0.66
     von
    -0.65
     the
    -0.65
     por
    -0.64
     and
    -0.64
     an
    -0.62
     ad
    -0.60
     who
    -0.59
    POSITIVE LOGITS
     Shakspeare
    1.11
    <bos>
    1.09
     Cæsar
    0.94
     Monfieur
    0.94
     myſelf
    0.88
     Shaksp
    0.88
     Sarm
    0.84
    verwijspagina
    0.80
     morrow
    0.79
     ་་
    0.79
    Activations Density 2.156%

    No Known Activations