© 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. 5527
    Prev
    Next
    INDEX
    Explanations

    capitalized sentence starters, especially "A" followed by other words

    oai_token-act-pair · gemini-2.0-flash

    A

    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
    principalTable
    -0.89
     disambiguazione
    -0.87
    rungsseite
    -0.82
    awtextra
    -0.81
     cherchés
    -0.77
     resourceCulture
    -0.77
    ]")]
    -0.77
     '\\;'
    -0.76
    tagHelperRunner
    -0.75
     Roskov
    -0.75
    POSITIVE LOGITS
     quick
    0.66
    maal
    0.59
     huge
    0.57
     big
    0.56
     little
    0.56
     friend
    0.55
     great
    0.54
     large
    0.52
     keen
    0.52
    EXPR
    0.52
    Activations Density 2.037%

    No Known Activations