© 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. 1410
    Prev
    Next
    INDEX
    Explanations

    words that either indicate an official statement or that express a specific point amidst related information

    oai_token-act-pair · gemini-2.0-flash

    statements and reports

    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
    principalTable
    -0.64
     defaultstate
    -0.56
     ModelExpression
    -0.54
     Drapeau
    -0.54
    Rhestr
    -0.52
    unicaciones
    -0.52
    üyada
    -0.52
    脚注の使い方
    -0.51
    Preparazione
    -0.50
    öglichkeiten
    -0.48
    POSITIVE LOGITS
    StoryboardSegue
    0.65
    олові
    0.58
    FormTagHelper
    0.56
    WriteAttribute
    0.52
    __(/*!
    0.50
    UnknownFields
    0.49
    Style
    0.49
    UIControlState
    0.49
    Subviews
    0.48
     <<<<<<<<<<<<<<
    0.48
    Activations Density 7.737%

    No Known Activations