© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 638
    Prev
    Next
    INDEX
    Explanations

    blocks of text relating to scientific and legal papers

    oai_token-act-pair · gemini-2.0-flash

    Technical documents

    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
    ReusableCell
    -0.57
     bells
    -0.50
     sneaky
    -0.48
     néz
    -0.47
    shoes
    -0.47
    issors
    -0.46
    Smash
    -0.46
     MainAxisSize
    -0.46
     checkers
    -0.45
    Sucesor
    -0.45
    POSITIVE LOGITS
     Consideration
    0.48
     Theſe
    0.47
     Enrichment
    0.47
     Diſ
    0.47
     Inſ
    0.46
     الرياضيه
    0.45
     Standardization
    0.44
     Improvement
    0.44
     Examinations
    0.43
     Stabilization
    0.43
    Activations Density 14.368%

    No Known Activations