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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6352
    Prev
    Next
    INDEX
    Explanations

    instances of the auxiliary verbs 'have' and 'be' appearing together in the past or present perfect tenses.

    oai_token-act-pair · gemini-2.0-flash

    Describing research

    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
    RegistryLite
    -0.77
     '\\;'
    -0.76
     been
    -0.65
     Roskov
    -0.61
    ]-->
    -0.61
     الحره
    -0.58
    optarg
    -0.57
     ttk
    -0.57
    GraphicsUnit
    -0.56
     BEEN
    -0.55
    POSITIVE LOGITS
     have
    0.58
     executed
    0.54
    have
    0.54
     carried
    0.54
     encountered
    0.53
     monitored
    0.50
    goa
    0.50
     promoted
    0.50
     pursued
    0.50
     sampled
    0.48
    Activations Density 4.347%

    No Known Activations