© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14144
    Prev
    Next
    INDEX
    Explanations

    capitalized words and phrases that are political in nature or function as announcements

    oai_token-act-pair · gemini-2.0-flash

    Random postings and comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     saites
    -0.60
    ällor
    -0.54
     extracts
    -0.49
    ligente
    -0.48
     covers
    -0.48
    parseColor
    -0.48
     comen
    -0.47
    arise
    -0.47
     IS
    -0.47
    ar
    -0.47
    POSITIVE LOGITS
    yntaxException
    0.58
    principalTable
    0.53
    ContentAsync
    0.53
    tonode
    0.51
     Signalez
    0.50
    发表于
    0.49
    twimg
    0.48
    templateUrl
    0.48
    LabelTagHelper
    0.47
    <caption>
    0.46
    Activations Density 2.975%

    No Known Activations