© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11440
    Prev
    Next
    INDEX
    Explanations

    positive subjective descriptors of food and experiences

    oai_token-act-pair · gemini-2.0-flash

    adequacy

    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
     Мексичка
    -0.64
    ياء
    -0.61
     MainAxisSize
    -0.60
    ########.
    -0.59
     للمعارف
    -0.57
    oredCriteria
    -0.57
     فريبيس
    -0.56
     >=",
    -0.53
    ).}
    -0.52
    ()]);
    -0.52
    POSITIVE LOGITS
    Mozilla
    0.51
    jsxFileName
    0.47
     emb
    0.46
     belangrij
    0.44
     SEDS
    0.43
    pfel
    0.43
    ResponseWriter
    0.42
    Unmarshaller
    0.42
    GRANTED
    0.42
     Hebron
    0.42
    Activations Density 0.202%

    No Known Activations