© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10592
    Prev
    Next
    INDEX
    Explanations

    a wide range of words and phrases, often related to dialogue, personal opinions, and storytelling, but also some words related to technical contexts.

    oai_token-act-pair · gemini-2.0-flash

    Disbelief, errors, reprimands

    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
     >=",
    -0.77
     ?',
    -0.69
     referenties
    -0.66
    ]),
    -0.60
    ⓧ
    -0.59
     ?";
    -0.58
    ionales
    -0.57
    otry
    -0.57
     TestBed
    -0.56
     parameterized
    -0.56
    POSITIVE LOGITS
    хьтан
    0.82
     насељу
    0.56
     Administrativna
    0.50
    RegressionTest
    0.49
    esModule
    0.49
     Wikispecies
    0.47
    enegro
    0.47
    MethodManager
    0.47
     hot
    0.45
    hot
    0.45
    Activations Density 0.331%

    No Known Activations