© 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. 6377
    Prev
    Next
    INDEX
    Explanations

    capitalized letters or symbols within technical documents

    oai_token-act-pair · gemini-2.0-flash

    say hyphenated words

    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
     الحره
    -1.27
    mybatisplus
    -1.11
     estekak
    -1.04
     صوتيه
    -1.03
    TagMode
    -1.02
    Билгалдахарш
    -0.98
    SequentialGroup
    -0.97
    SourceChecksum
    -0.97
     betweenstory
    -0.96
     esternos
    -0.86
    POSITIVE LOGITS
    <strong>
    0.66
    Z
    0.59
    G
    0.57
    //
    0.56
    <b>
    0.56
    L
    0.55
    V
    0.55
    ta
    0.54
    R
    0.54
    #
    0.52
    Activations Density 0.927%

    No Known Activations