© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9010
    Prev
    Next
    INDEX
    Explanations

    place names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     achtergrond
    -0.42
    a
    -0.40
    อล
    -0.39
    フラ
    -0.38
    ultier
    -0.37
    flake
    -0.36
    {"
    -0.35
     a
    -0.35
    AutoScaleMode
    -0.35
    երի
    -0.35
    POSITIVE LOGITS
     defaultstate
    1.08
    XmlAccessorType
    0.93
     purpoſe
    0.88
    TagMode
    0.82
    DeleteBehavior
    0.82
    sidemargin
    0.79
    UnusedPrivate
    0.77
     myſelf
    0.77
     pleaſure
    0.77
    CompilerServices
    0.76
    Activations Density 1.241%

    No Known Activations