© 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. 15237
    Prev
    Next
    INDEX
    Explanations

    last names and prefixes used in academic citations

    oai_token-act-pair · gemini-2.0-flash

    Cher

    np_max-act · 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
    adaptiveStyles
    -0.58
    anyahu
    -0.49
    rália
    -0.47
     hit
    -0.47
    )];
    -0.46
    yttö
    -0.44
     Heer
    -0.44
     mogelijk
    -0.44
     very
    -0.44
     }}"></
    -0.44
    POSITIVE LOGITS
    SharedCtor
    0.73
     Roskov
    0.72
     propOrder
    0.71
    CodeAttribute
    0.70
     للاسماء
    0.61
     tavola
    0.59
     @"/
    0.56
    OGND
    0.54
     reaſon
    0.52
    Personendaten
    0.52
    Activations Density 0.181%

    No Known Activations