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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9710
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated tokens, including brackets, 'buffer', and words associated with responsibility in research

    oai_token-act-pair · gemini-2.0-flash

    programming 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     multi
    -0.50
     Multi
    -0.48
    ↵↵
    -0.47
    -
    -0.47
     inner
    -0.46
    tem
    -0.45
     &
    -0.45
    res
    -0.45
    thi
    -0.44
     outer
    -0.44
    POSITIVE LOGITS
     myſelf
    0.94
     snippetHide
    0.91
    HasForeignKey
    0.90
    setVerticalGroup
    0.90
    }],
    0.86
    tvguidetime
    0.82
    IsMutable
    0.82
    Hentet
    0.81
     Efq
    0.80
     GenerationType
    0.79
    Activations Density 0.120%

    No Known Activations