© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11488
    Prev
    Next
    INDEX
    Explanations

    code blocks that are labeled with curly braces or colons

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -0.94
     Theſe
    -0.82
     itſelf
    -0.82
     myſelf
    -0.77
     purpoſe
    -0.75
     Monfieur
    -0.75
     theſe
    -0.75
     becauſe
    -0.73
     ainfi
    -0.73
     pleaſure
    -0.72
    POSITIVE LOGITS
    #
    0.54
    res
    0.53
    </i>
    0.52
     Stage
    0.52
     
    0.51
     calendriers
    0.50
    enumi
    0.50
    splitContainer
    0.50
    4
    0.49
            
    0.49
    Activations Density 8.432%

    No Known Activations