© 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. 15398
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations, places, and people

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    cipar
    -0.65
     It
    -0.63
    lour
    -0.60
    -
    -0.60
    lor
    -0.56
    WebVitals
    -0.56
    KeyPressed
    -0.54
    rance
    -0.54
    baa
    -0.53
    ̀nh
    -0.53
    POSITIVE LOGITS
     ainfi
    0.93
     auroit
    0.85
     feroit
    0.84
    Personendaten
    0.82
    ganggu
    0.81
     stället
    0.77
     vectorielle
    0.75
     peindre
    0.74
     normaux
    0.74
     öpp
    0.74
    Activations Density 15.339%

    No Known Activations