© 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. 3132
    Prev
    Next
    INDEX
    Explanations

    uses of the word "the" and related common words like "do" or "a"

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    monials
    -0.52
    ỡng
    -0.51
    ništvo
    -0.48
    為に
    -0.47
    shiro
    -0.46
    <<(
    -0.46
    quier
    -0.45
     INTERESAR
    -0.44
     fides
    -0.44
     Betracht
    -0.43
    POSITIVE LOGITS
    AndroidJUnit
    0.71
     ostavi
    0.68
    '},
    0.65
    Personendaten
    0.56
    parsedMessage
    0.54
     Upstream
    0.54
    +#+
    0.52
    )++;
    0.51
    '></
    0.50
     downstream
    0.50
    Activations Density 11.051%

    No Known Activations