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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5526
    Prev
    Next
    INDEX
    Explanations

    statements about historical events

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms related to layout and assembly

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    Rujuakan
    -0.65
    quième
    -0.55
     restent
    -0.54
    UrlResolution
    -0.52
    #
    -0.52
    exprimer
    -0.52
    arrêter
    -0.52
     newbie
    -0.52
    Vidite
    -0.51
    Kjelder
    -0.51
    POSITIVE LOGITS
    PerformLayout
    0.57
     AssemblyCulture
    0.56
     CreateTagHelper
    0.55
     chromat
    0.52
    ouna
    0.49
    shells
    0.48
     MainAxisSize
    0.48
    getSubject
    0.48
     phase
    0.47
    eqn
    0.47
    Activations Density 0.960%

    No Known Activations