© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15232
    Prev
    Next
    INDEX
    Explanations

    legal documents and terminology related to options, appeals, and time limits

    oai_token-act-pair · gemini-2.0-flash

    time

    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
     betweenstory
    -0.84
     nawr
    -0.77
    setVerticalGroup
    -0.71
     MainAxisSize
    -0.70
    TemporalType
    -0.70
    OpenHelper
    -0.66
    jsonwebtoken
    -0.66
    expandindo
    -0.65
    ueuse
    -0.64
    зулта
    -0.63
    POSITIVE LOGITS
    BASEPATH
    0.53
    lié
    0.47
     frame
    0.47
    mendations
    0.46
     grace
    0.44
    <bos>
    0.43
     extension
    0.42
     by
    0.40
    liar
    0.39
     of
    0.39
    Activations Density 4.708%

    No Known Activations