© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1467
    Prev
    Next
    INDEX
    Explanations

    words and phrases that signal conflict or dramatic tension

    oai_token-act-pair · gemini-2.0-flash

    Rising conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    UpdateCommand
    -0.45
    ,
    -0.41
     —
    -0.41
    Able
    -0.40
    Fac
    -0.39
    ledad
    -0.39
    fac
    -0.38
     encar
    -0.38
    кновен
    -0.38
    jaya
    -0.36
    POSITIVE LOGITS
    MigrationBuilder
    0.75
     للمعارف
    0.69
     للاسماء
    0.67
    riebene
    0.67
    下载附件
    0.67
     مرئيه
    0.66
     ProtoMessage
    0.66
     Theſe
    0.66
     تانيه
    0.66
     itſelf
    0.65
    Activations Density 1.539%

    No Known Activations