© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4630
    Prev
    Next
    INDEX
    Explanations

    negative sentiment towards organizations or people, including named entities like "black", "Iran", "California", "Army" and "Christian".

    oai_token-act-pair · gemini-2.0-flash

    among

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SequentialGroup
    -0.62
    Skocz
    -0.61
     corsa
    -0.59
     AssemblyVersion
    -0.58
     nakalista
    -0.55
    Manbalar
    -0.55
    BufferException
    -0.54
    essa
    -0.52
    GridItem
    -0.52
    脚注の使い方
    -0.51
    POSITIVE LOGITS
     hinweg
    0.56
     obicei
    0.52
     čier
    0.52
     الدولى
    0.48
     nonverbal
    0.47
    Datuak
    0.46
    MenuInflater
    0.45
     myndig
    0.45
    andere
    0.44
     lī
    0.44
    Activations Density 3.938%

    No Known Activations