© 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. 15098
    Prev
    Next
    INDEX
    Explanations

    code related to conditional compilation

    oai_token-act-pair · gemini-2.0-flash

    endif

    np_max-act · gemini-2.0-flash

    endif

    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
     Efq
    -2.33
     myſelf
    -2.16
     itſelf
    -2.06
     doubtnut
    -2.03
     Theſe
    -2.00
    ſelf
    -1.90
     Jefus
    -1.90
    ^(@)
    -1.84
    ſelves
    -1.84
     themſelves
    -1.82
    POSITIVE LOGITS
    ↵↵
    1.16
     
    1.12
    -
    1.03
    .
    1.02
    ,
    1.02
    ↵
    0.99
    /
    0.97
    en
    0.96
    <strong>
    0.95
     or
    0.94
    Activations Density 0.757%

    No Known Activations