© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14329
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and nouns combined with other words

    oai_token-act-pair · gemini-2.0-flash

    stop

    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
     stop
    -1.58
    stop
    -1.44
     stops
    -1.42
     Stop
    -1.38
     stopped
    -1.38
     stopping
    -1.35
    Stop
    -1.32
    stops
    -1.30
     STOP
    -1.30
     Stops
    -1.28
    POSITIVE LOGITS
     gynnwys
    0.61
    idosis
    0.60
    ranslated
    0.57
     Bourgoin
    0.55
     ویکی‌آمباردا
    0.54
     nakalista
    0.52
    itária
    0.50
     Azad
    0.50
    hoodie
    0.49
    lück
    0.49
    Activations Density 52.852%

    No Known Activations