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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4035
    Prev
    Next
    INDEX
    Explanations

    references to other research and the word "LTD" (long-term depression)

    oai_token-act-pair · gemini-2.0-flash

    research papers

    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
    ."]
    -0.61
    ++
    
    -0.57
    ...')
    -0.57
    »-
    -0.57
    ?")
    -0.55
    _
    
    -0.55
    .")
    
    -0.54
     $\}$
    -0.54
     }</
    -0.54
    )":
    -0.54
    POSITIVE LOGITS
    thique
    0.61
     aeruginosa
    0.61
     doInBackground
    0.57
     оригіналу
    0.57
    قایناقلار
    0.56
    ingan
    0.54
     Dickerson
    0.54
    Przypisy
    0.54
    Kjelder
    0.54
     Hickman
    0.54
    Activations Density 30.555%

    No Known Activations