© 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. 4430
    Prev
    Next
    INDEX
    Explanations

    instances of people expressing their opinions or positions, often specifically targeting groups of people

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     Baillargeon
    -0.66
     مشين
    -0.52
     marinho
    -0.51
    ற்ப
    -0.50
     resourceCulture
    -0.49
     Wiktionnaire
    -0.49
    vestres
    -0.48
     flesta
    -0.47
     générales
    -0.46
    iedenis
    -0.46
    POSITIVE LOGITS
    complexType
    0.69
     onAnimation
    0.60
    uesday
    0.57
    帖最后由
    0.55
    <?
    0.53
    zeiti
    0.53
    فحة
    0.52
    JKLM
    0.52
     đãi
    0.51
     CommonModule
    0.50
    Activations Density 6.707%

    No Known Activations