© 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. 12545
    Prev
    Next
    INDEX
    Explanations

    words related to the number 'one'

    oai_token-act-pair · gemini-2.0-flash

    Code/technical documentation

    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
     shared
    -0.74
    shared
    -0.69
     Shared
    -0.68
     gemens
    -0.67
     common
    -0.64
     chung
    -0.62
     overal
    -0.62
    Shared
    -0.62
     einheit
    -0.60
     overarching
    -0.59
    POSITIVE LOGITS
     insuffisamment
    0.81
    UnsafeEnabled
    0.62
    oredCriteria
    0.60
     resourceCulture
    0.54
    Manbalar
    0.51
     useHistory
    0.51
    :+:
    0.51
    tonode
    0.51
     bire
    0.50
    MessageTagHelper
    0.50
    Activations Density 2.021%

    No Known Activations