© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3627
    Prev
    Next
    INDEX
    Explanations

    phrases involving movement from one place to another

    oai_token-act-pair · gemini-2.0-flash

    Entering or circulating

    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
    elesai
    -0.57
     caractéristique
    -0.55
     ongles
    -0.54
     Efq
    -0.54
     dessous
    -0.52
     uncin
    -0.52
    dersfield
    -0.52
     agrí
    -0.50
     réflé
    -0.49
     détach
    -0.49
    POSITIVE LOGITS
     mainstream
    0.68
     stream
    0.58
    TintMode
    0.57
    scheme
    0.56
     orbit
    0.54
    politico
    0.53
    +#+
    0.53
    Scheme
    0.52
    XMLSchema
    0.52
     band
    0.52
    Activations Density 1.159%

    No Known Activations