© 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. 5546
    Prev
    Next
    INDEX
    Explanations

    words with 1 to 3 characters and some short phrases

    oai_token-act-pair · gemini-2.0-flash

    Cut-off text snippets

    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
     mergeFrom
    -0.67
     policiais
    -0.63
     Dalio
    -0.63
    iastes
    -0.62
     Utara
    -0.60
     mathématiques
    -0.59
    ValueStyle
    -0.59
     élector
    -0.58
     AssemblyProduct
    -0.57
    pulumi
    -0.56
    POSITIVE LOGITS
     referrerpolicy
    0.60
     **/
    
    0.57
    """,
    0.54
    }")
    
    0.54
    //}
    
    0.54
    '],$
    0.53
    --*/
    0.53
    ])
    
    0.53
    '])
    
    0.52
    **/
    
    0.49
    Activations Density 20.756%

    No Known Activations