© 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. 3413
    Prev
    Next
    INDEX
    Explanations

    the word "why", "how" or "what"

    oai_token-act-pair · gemini-2.0-flash

    question words

    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
    ########.
    -0.83
     how
    -0.79
    httphttps
    -0.76
    ]<<"
    -0.71
     thither
    -0.68
     prioritizing
    -0.68
     stabilization
    -0.68
     figliu
    -0.68
    IsContent
    -0.67
    tvguidetime
    -0.65
    POSITIVE LOGITS
    Демографія
    0.57
    прочем
    0.56
    ypress
    0.54
    tanleria
    0.52
    .
    0.51
    ,
    0.50
    lamydia
    0.50
    PRESA
    0.49
     Zwar
    0.48
    ↵↵
    0.47
    Activations Density 0.211%

    No Known Activations