© 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. 6449
    Prev
    Next
    INDEX
    Explanations

    numbers and sometimes the word "Review"

    oai_token-act-pair · gemini-2.0-flash

    say "hyphens"

    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
     referenties
    -0.94
    __':
    -0.91
     >=",
    -0.83
    __":
    -0.81
     Савезне
    -0.80
    Geplaatst
    -0.79
    parsedMessage
    -0.77
    expandindo
    -0.75
    цездатний
    -0.75
    UserScript
    -0.73
    POSITIVE LOGITS
    A
    0.46
     decembrie
    0.44
     Púb
    0.44
    -
    0.44
    manage
    0.42
     -
    0.42
    KI
    0.41
    0
    0.41
    안
    0.40
    LEVEL
    0.40
    Activations Density 0.917%

    No Known Activations