© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13312
    Prev
    Next
    INDEX
    Explanations

    a variety of word fragments and word endings that don't seem to have a central theme

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    تقاوى
    -0.66
    stdc
    -0.65
    Bakgrunnsstoff
    -0.65
    %</
    -0.60
    AnchorStyles
    -0.60
    ="@+
    -0.55
    ]=-
    -0.55
    !*\
    -0.54
    ']."
    -0.54
    "](
    -0.54
    POSITIVE LOGITS
     vérit
    0.51
     rêver
    0.51
     république
    0.51
     économiques
    0.50
     financières
    0.49
     igång
    0.49
     varandra
    0.49
     chaînes
    0.48
     gesteld
    0.48
    Specification
    0.47
    Activations Density 0.373%

    No Known Activations