© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6602
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by words like said or declared

    oai_token-act-pair · gemini-2.0-flash

    words related to speech

    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
    dero
    -0.54
     }.
    -0.54
     grand
    -0.53
    artifactId
    -0.48
    ándola
    -0.47
    ########.
    -0.47
    zean
    -0.47
     binary
    -0.46
     wunderbar
    -0.46
    Bibliograf
    -0.46
    POSITIVE LOGITS
     said
    0.66
    Посилання
    0.63
     told
    0.62
    contentValues
    0.60
     explained
    0.58
     argued
    0.57
    hints
    0.57
    CopyWith
    0.56
    UnusedPrivate
    0.56
    iprot
    0.54
    Activations Density 0.734%

    No Known Activations