© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5326
    Prev
    Next
    INDEX
    Explanations

    words or phrases involving numbers, probabilities, statistics, or ranges

    oai_token-act-pair · gemini-2.0-flash

    range

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     EconPapers
    -0.73
     تكبرها
    -0.73
    endphp
    -0.66
    
    -0.65
    MetaType
    -0.63
     StringTokenizer
    -0.63
     câte
    -0.59
     simplifié
    -0.56
     Réponses
    -0.56
     légende
    -0.55
    POSITIVE LOGITS
     range
    1.02
    range
    0.83
     ranges
    0.83
     Range
    0.77
    Range
    0.73
     variation
    0.71
     close
    0.70
    +/-
    0.69
     Ranges
    0.69
     +/-
    0.69
    Activations Density 2.639%

    No Known Activations