© 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. 10957
    Prev
    Next
    INDEX
    Explanations

    the word "consequences" followed or preceded by words about computers and negative events

    oai_token-act-pair · gemini-2.0-flash

    consequence

    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
     EconPapers
    -1.17
    tagHelperRunner
    -1.15
     للمعارف
    -1.15
     aidant
    -0.99
    StoryboardSegue
    -0.96
    Tembelea
    -0.96
     فريبيس
    -0.96
    ագրություններ
    -0.95
    tvguidetime
    -0.95
     يتيمه
    -0.94
    POSITIVE LOGITS
    The
    0.79
    1
    0.71
    \
    0.71
    <strong>
    0.69
    With
    0.66
    I
    0.66
    4
    0.66
    2
    0.65
    3
    0.65
    (
    0.63
    Activations Density 1.021%

    No Known Activations