© 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. 7128
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "composed of" or "consisting of" or variants of compose

    oai_token-act-pair · gemini-2.0-flash

    composed

    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
    ValueStyle
    -1.07
     EconPapers
    -0.95
    protoimpl
    -0.91
     kasarigan
    -0.90
     referrerpolicy
    -0.89
    enderror
    -0.79
    脚注の使い方
    -0.78
    saraba
    -0.77
    Personendaten
    -0.77
    PerformLayout
    -0.75
    POSITIVE LOGITS
     consists
    1.80
     consisting
    1.78
     consist
    1.70
     consisted
    1.63
     composed
    1.61
     comprised
    1.55
     comprises
    1.41
     comprising
    1.40
     terdiri
    1.38
     comprise
    1.37
    Activations Density 1.890%

    No Known Activations