© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10213
    Prev
    Next
    INDEX
    Explanations

    words related to past or present states of being, often in the context of actions, feelings, or time

    oai_token-act-pair · gemini-2.0-flash

    verbs

    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
     Lightboxes
    -0.64
     nød
    -0.59
     mennes
    -0.56
     '\\;'
    -0.54
    ędziesz
    -0.51
    StoryboardSegue
    -0.51
     solteiro
    -0.51
    afficheront
    -0.50
    CloseOperation
    -0.49
    tymologie
    -0.49
    POSITIVE LOGITS
     determine
    0.82
     threaten
    0.74
     restore
    0.73
     prepare
    0.71
     consider
    0.71
     compare
    0.71
     allow
    0.71
     return
    0.71
     deceive
    0.71
     celebrate
    0.70
    Activations Density 8.301%

    No Known Activations