© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5560
    Prev
    Next
    INDEX
    Explanations

    fragments of code or configuration files

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     contemplate
    -0.50
    scot
    -0.47
     contemplating
    -0.46
    رياض
    -0.45
     liberally
    -0.45
     inescapable
    -0.44
    utuhkan
    -0.44
     enduring
    -0.44
    himself
    -0.44
    determination
    -0.44
    POSITIVE LOGITS
    timg
    0.59
    piram
    0.52
    </caption>
    0.52
     autorytatywna
    0.51
    addGap
    0.50
    jgl
    0.48
     Url
    0.47
    ]}>
    0.47
    tagHelperRunner
    0.46
    DllImport
    0.46
    Activations Density 27.177%

    No Known Activations