© 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. 1229
    Prev
    Next
    INDEX
    Explanations

    words with the suffixes "ness" and "'s" and good things that happened at night

    oai_token-act-pair · gemini-2.0-flash

    Apostrophes

    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
    FailureListener
    -0.60
    :✨
    -0.59
    TypedDataSet
    -0.55
    -------------</
    -0.55
    jfree
    -0.55
     jPanel
    -0.52
    CROSSTALK
    -0.52
    Portail
    -0.52
    }")
    -0.51
    belline
    -0.50
    POSITIVE LOGITS
    ’
    1.12
    '
    1.08
    $'
    0.88
    ningens
    0.67
    ´
    0.63
    \'
    0.62
    }'
    0.62
    ന്റെ
    0.60
    ’
    0.58
    ]'
    0.57
    Activations Density 1.401%

    No Known Activations