© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13907
    Prev
    Next
    INDEX
    Explanations

    descriptive verbs and adjectives related to physical actions, emotions, and mechanics

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     was
    -0.59
     бы
    -0.55
     au
    -0.54
     
    -0.48
     a
    -0.48
     to
    -0.47
     lalu
    -0.46
     went
    -0.45
     moved
    -0.44
     that
    -0.44
    POSITIVE LOGITS
     pleaſure
    1.05
     Theſe
    0.96
     EconPapers
    0.96
     itſelf
    0.95
     Houſe
    0.94
     purpoſe
    0.94
     myſelf
    0.91
     fhew
    0.91
     Reſ
    0.90
     becauſe
    0.90
    Activations Density 10.740%

    No Known Activations