© 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. 14918
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a variety of different words depending on surrounding words, but in general it seems to activate on some numbers in text and some words with the suffix -tion

    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
     <=",
    -0.62
    Hentet
    -0.56
     sessile
    -0.54
    ̯
    -0.53
    //
    -0.52
    esm
    -0.52
    quil
    -0.52
    ESM
    -0.51
     strto
    -0.50
    rizona
    -0.50
    POSITIVE LOGITS
    <bos>
    0.57
    homonymie
    0.54
    ():
    0.49
    ();*/
    0.48
    "]:
    0.48
    `);
    0.48
    `}
    0.48
    كويكب
    0.47
    **/
    0.46
     "..\..\
    0.45
    Activations Density 7.585%

    No Known Activations