© 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. 8966
    Prev
    Next
    INDEX
    Explanations

    mathematical or calculus equations and expressions

    oai_token-act-pair · gemini-2.0-flash

    math problems

    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
     Monfieur
    -0.52
     ſhe
    -0.52
     dafs
    -0.48
     pleaſure
    -0.47
     ſeveral
    -0.47
     havaianas
    -0.45
     miſ
    -0.45
     fhort
    -0.45
     houſe
    -0.44
     deſt
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    1.05
    "):
    
    0.97
    }")
    
    0.97
    ]));
    
    0.96
     الحره
    0.96
    ]))
    
    0.95
    ])))
    0.95
    EndGlobalSection
    0.93
    )))
    
    0.93
     CreateTagHelper
    0.93
    Activations Density 15.922%

    No Known Activations