© 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. 11895
    Prev
    Next
    INDEX
    Explanations

    HTML markup tags and Javascript syntax

    oai_token-act-pair · gemini-2.0-flash

    id

    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
    RenderAtEndOf
    -1.40
     Efq
    -1.33
    AndEndTag
    -1.31
     itſelf
    -1.31
     Monfieur
    -1.30
     myſelf
    -1.27
     themſelves
    -1.26
     purpoſe
    -1.25
     pleaſure
    -1.22
     EconPapers
    -1.21
    POSITIVE LOGITS
    ,
    0.75
     
    0.73
    .
    0.69
    :
    0.63
    )
    0.57
     '
    0.53
     ‘
    0.53
     (
    0.53
    >
    0.52
     ev
    0.51
    Activations Density 2.007%

    No Known Activations