© 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. 13100
    Prev
    Next
    INDEX
    Explanations

    words used to mark the cause and effect of an action

    oai_token-act-pair · gemini-2.0-flash

    Quotes and questions

    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
     виправивши
    -0.85
     Савезне
    -0.84
     يتيمه
    -0.82
     '\\;'
    -0.79
     oprot
    -0.67
     EClass
    -0.66
    featureID
    -0.61
     bezeichneter
    -0.61
     كومونز
    -0.61
    UnsafeEnabled
    -0.61
    POSITIVE LOGITS
     similarly
    0.47
     equally
    0.44
    不自
    0.43
    مرار
    0.42
     der
    0.42
     balances
    0.41
    に通
    0.41
    DataSnapshot
    0.41
    ScopeManager
    0.40
     again
    0.40
    Activations Density 1.043%

    No Known Activations