© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5334
    Prev
    Next
    INDEX
    Explanations

    the word "last", but also sometimes finds related terms like "final", "previous", or "middle."

    oai_token-act-pair · gemini-2.0-flash

    last

    np_max-act · gemini-2.0-flash

    last

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Walkover
    -0.75
    Personensuche
    -0.72
     estekak
    -0.72
    QMetaType
    -0.71
    ValueStyle
    -0.69
     betweenstory
    -0.68
    sizeCache
    -0.68
    CPtr
    -0.67
     חיצוניים
    -0.65
    پیوند
    -0.65
    POSITIVE LOGITS
     nation
    0.60
    cdnjs
    0.59
     nations
    0.56
     Whilst
    0.55
    Whilst
    0.54
    ]")]
    0.52
    __*/
    0.51
    oughlin
    0.50
     USA
    0.50
    ://
    0.50
    Activations Density 1.586%

    No Known Activations