© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12653
    Prev
    Next
    INDEX
    Explanations

    mentions of recent activity in the past

    oai_token-act-pair · gemini-2.0-flash

    Recounting experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Personensuche
    -0.82
    Autoritní
    -0.77
    SourceChecksum
    -0.71
    TagMode
    -0.65
    ftagPool
    -0.59
    sidemargin
    -0.55
    ########.
    -0.54
    UnusedPrivate
    -0.54
    portál
    -0.52
     AssemblyTitle
    -0.52
    POSITIVE LOGITS
    Newswire
    0.56
    EndContext
    0.56
    Clik
    0.52
    ForValue
    0.49
    BURY
    0.49
    ́ng
    0.47
    createClass
    0.46
    apture
    0.45
    Getenv
    0.45
    MIB
    0.45
    Activations Density 0.178%

    No Known Activations