© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4248
    Prev
    Next
    INDEX
    Explanations

    sentences that include the word "you" followed by verbs indicating ability or access

    oai_token-act-pair · gemini-2.0-flash

    enabling digital functionality

    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
    ffre
    -0.59
    ibouti
    -0.55
    orghini
    -0.50
     players
    -0.50
    ographi
    -0.49
     previa
    -0.49
     financière
    -0.49
    alba
    -0.49
    oa̍t
    -0.48
    IBinder
    -0.48
    POSITIVE LOGITS
    LabelTagHelper
    0.62
    SourceChecksum
    0.56
     personalise
    0.56
     manage
    0.56
     conduct
    0.52
     intuitively
    0.51
     незавершена
    0.51
     sẻ
    0.50
     vastaan
    0.50
    parsedMessage
    0.49
    Activations Density 1.230%

    No Known Activations