© 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. 4254
    Prev
    Next
    INDEX
    Explanations

    words/phrases implying a positive qualitative assessment

    oai_token-act-pair · gemini-2.0-flash

    pretty

    np_max-act · gemini-2.0-flash

    pretty

    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
    хьтан
    -0.85
    ItemBackground
    -0.84
    ьаж
    -0.82
     cdti
    -0.81
     CWE
    -0.79
    ########.
    -0.78
    IsMutable
    -0.75
     InputDecoration
    -0.75
     actionMode
    -0.74
     rhestr
    -0.73
    POSITIVE LOGITS
    e
    0.82
     The
    0.73
    i
    0.71
     Each
    0.69
    a
    0.69
    ↵
    0.69
     
    0.68
     Most
    0.65
    ↵↵
    0.65
    <h2>
    0.64
    Activations Density 1.944%

    No Known Activations