© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5204
    Prev
    Next
    INDEX
    Explanations

    indefinite articles, especially "a" preceding descriptive adjectives.

    oai_token-act-pair · gemini-2.0-flash

    strong opinions/language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     charité
    -0.51
     belas
    -0.51
     newBuilder
    -0.50
    zná
    -0.50
     actes
    -0.49
     caduta
    -0.47
     difficulté
    -0.47
     bonté
    -0.46
     judiciales
    -0.46
     parç
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    0.86
     houſe
    0.75
    UALA
    0.68
     Efq
    0.67
     Etr
    0.66
     anvil
    0.65
    nachron
    0.63
    #+#
    0.63
     coconut
    0.63
    nextProps
    0.63
    Activations Density 1.503%

    No Known Activations