© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9683
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated concepts, including Google search details, chemical names, and build numbers

    oai_token-act-pair · gemini-2.0-flash

    links and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     uſ
    -0.73
    ISupport
    -0.73
    Geplaatst
    -0.65
    ]")]
    -0.63
    ỡng
    -0.60
     régal
    -0.56
     AssemblyTitle
    -0.56
     stagione
    -0.56
     PublicKey
    -0.56
     endforeach
    -0.55
    POSITIVE LOGITS
    ()?;
    0.58
    artney
    0.58
    ginate
    0.54
    olge
    0.54
    gorithm
    0.51
     Google
    0.51
    unds
    0.48
     MEET
    0.47
    }/${
    0.47
    MEET
    0.46
    Activations Density 0.641%

    No Known Activations