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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 10538
    Prev
    Next
    INDEX
    Explanations

    academic citations

    oai_token-act-pair · gemini-2.0-flash

    citations and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    -0.79
     })
    
    -0.75
    ']))
    
    -0.74
     }</
    -0.72
    évaluateur
    -0.69
     }))
    -0.69
     الرياضيه
    -0.68
    '])->
    -0.68
    WithIOException
    -0.66
     ]
    
    -0.64
    POSITIVE LOGITS
    છ
    0.42
    夸
    0.39
    FOLD
    0.39
     sociales
    0.39
     creeping
    0.39
    това
    0.39
    phosph
    0.38
     rekening
    0.38
     delo
    0.38
    phospho
    0.38
    Activations Density 0.388%

    No Known Activations