© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13438
    Prev
    Next
    INDEX
    Explanations

    phrases including "to," "into," and potentially "a" that suggest transformation or conversion.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    -0.53
    OGND
    -0.51
    ้อย
    -0.46
     ihn
    -0.46
     SqlCommand
    -0.46
    glBind
    -0.45
     himſelf
    -0.44
     transformers
    -0.44
    πως
    -0.44
     Revelation
    -0.43
    POSITIVE LOGITS
    )</
    0.60
    encodeWith
    0.59
    ))->
    0.58
    "))
    
    0.57
    RTLD
    0.57
    )))
    
    0.57
    MessageTagHelper
    0.57
    )*/
    0.56
    "}")
    0.55
     *)(
    0.53
    Activations Density 1.495%

    No Known Activations