© 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. 15482
    Prev
    Next
    INDEX
    Explanations

    mentions of research, studies, papers, documentation, style and analysis.

    oai_token-act-pair · gemini-2.0-flash

    scholarly articles

    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
     focusing
    -0.59
     examines
    -0.58
     focus
    -0.57
     dealing
    -0.56
     examine
    -0.56
     tell
    -0.55
     address
    -0.55
     covering
    -0.54
    focus
    -0.53
    dealing
    -0.53
    POSITIVE LOGITS
    SequentialGroup
    0.76
     autorytatywna
    0.76
    رشف
    0.66
    +:+
    0.65
    InsertCommand
    0.63
    SEGUIR
    0.58
    Hentet
    0.56
     GenerationType
    0.56
     թվական
    0.55
     EdgeInsets
    0.54
    Activations Density 7.646%

    No Known Activations