© 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. 12212
    Prev
    Next
    INDEX
    Explanations

    equal signs in code

    oai_token-act-pair · gemini-2.0-flash

    =

    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
    protoimpl
    -0.62
     https
    -0.51
     Pop
    -0.49
    fastjson
    -0.46
     Bit
    -0.45
     batch
    -0.45
    spro
    -0.45
     ferons
    -0.44
     http
    -0.44
    lá
    -0.43
    POSITIVE LOGITS
     propOrder
    0.65
     ***!
    0.63
    ագրություններ
    0.63
    AccessorTable
    0.60
     صوتيه
    0.59
    ISupport
    0.57
     inol
    0.57
     unfortunately
    0.56
    usercontent
    0.54
     Scip
    0.54
    Activations Density 0.103%

    No Known Activations