© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13617
    Prev
    Next
    INDEX
    Explanations

    text describing speech, especially quotes by named people, with a bias towards the words "said" or "says", as well as some punctuation.

    oai_token-act-pair · gemini-2.0-flash

    quotes and dialogue attribution

    np_token-act-pair-logits · gpt-4o-mini

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    kháu
    -1.00
    SourceChecksum
    -0.96
    oa̍t
    -0.84
     الرياضيه
    -0.82
    TagMode
    -0.81
    LookAnd
    -0.77
     <>",
    -0.73
    endphp
    -0.73
    XmlType
    -0.70
     ddelweddau
    -0.69
    POSITIVE LOGITS
     paid
    0.47
     said
    0.47
    منابع
    0.42
     explained
    0.41
     clarified
    0.40
    coglie
    0.39
     offered
    0.39
    Explanation
    0.39
     pool
    0.39
    برا
    0.38
    Activations Density 0.652%

    No Known Activations