© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5452
    Prev
    Next
    INDEX
    Explanations

    code snippets including keywords like EXTRA, FOLDER, TAG, and SECTION

    oai_token-act-pair · gemini-2.0-flash

    underscore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ſche
    -0.88
     ſtate
    -0.84
     purpoſe
    -0.80
     ftate
    -0.80
     houſe
    -0.79
     perfons
    -0.76
     Perſ
    -0.75
     Jefus
    -0.75
    väg
    -0.74
     ſch
    -0.73
    POSITIVE LOGITS
     As
    0.48
     sa
    0.48
     una
    0.47
    ]))
    0.46
     so
    0.46
     ho
    0.44
     er
    0.43
     It
    0.43
     en
    0.43
     His
    0.42
    Activations Density 4.836%

    No Known Activations