© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11137
    Prev
    Next
    INDEX
    Explanations

    scientific writing discussing research results

    oai_token-act-pair · gemini-2.0-flash

    importance/urgency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    flink
    -0.58
    География
    -0.55
    djangoproject
    -0.54
    HtmlAttribute
    -0.52
     Partagez
    -0.50
    verifyException
    -0.48
    ushman
    -0.48
    photobucket
    -0.48
     aapt
    -0.47
     onAnimation
    -0.47
    POSITIVE LOGITS
     EClass
    0.61
     of
    0.60
    /**
    0.58
    rungsseite
    0.52
    HasForeignKey
    0.51
    RuleContext
    0.50
     يتيمه
    0.48
    WithIOException
    0.48
     Ανακτήθηκε
    0.47
    tagHelper
    0.47
    Activations Density 2.927%

    No Known Activations