© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15221
    Prev
    Next
    INDEX
    Explanations

    the "@" symbol followed by specific character patterns related to code or referencing other sources.

    oai_token-act-pair · gemini-2.0-flash

    (@

    np_max-act · gemini-2.0-flash

    @

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     @
    -1.26
    @
    -1.09
    (@
    -0.82
    ↵↵
    -0.77
     (@
    -0.73
    ’
    -0.70
    //
    -0.67
     //
    -0.66
    M
    -0.65
    I
    -0.62
    POSITIVE LOGITS
     Theſe
    1.00
     itſelf
    1.00
    ]$}
    0.96
     }}$}
    0.93
     ſtate
    0.93
     $_"
    0.90
     Houſe
    0.88
     houſe
    0.88
     Efq
    0.87
     becauſe
    0.84
    Activations Density 1.012%

    No Known Activations