© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15172
    Prev
    Next
    INDEX
    Explanations

    technical documents containing discussion of motion vectors and image processing

    oai_token-act-pair · gemini-2.0-flash

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     "
    -1.14
     '
    -1.12
    ↵↵
    -1.04
     (
    -0.96
    <eos>
    -0.94
     _
    -0.93
     *
    -0.92
     for
    -0.92
     +
    -0.91
    ,
    -0.90
    POSITIVE LOGITS
    UnusedPrivate
    1.91
    AndEndTag
    1.90
     doubtnut
    1.73
    LookAnd
    1.67
    NameInMap
    1.61
    StoryboardSegue
    1.60
     ―――――
    1.60
     photolibrary
    1.60
    تقاوى
    1.59
    expandindo
    1.59
    Activations Density 1.430%

    No Known Activations