© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11005
    Prev
    Next
    INDEX
    Explanations

    instances of someone illustrating a concept, as well as statements of potential utility or difficulty

    oai_token-act-pair · gemini-2.0-flash

    showing or explaining

    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
     proof
    -0.78
     Prove
    -0.73
     proofs
    -0.69
    Proof
    -0.68
    windowFixed
    -0.66
    RegressionTest
    -0.66
    Prove
    -0.65
     demostrar
    -0.65
    ]--;
    -0.64
    proof
    -0.64
    POSITIVE LOGITS
    NewUrlParser
    0.54
    які
    0.48
     confusion
    0.47
     confuse
    0.46
     confused
    0.45
     emot
    0.45
     lèvres
    0.44
     merak
    0.43
     erfahren
    0.43
    Fallback
    0.42
    Activations Density 0.989%

    No Known Activations