© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6462
    Prev
    Next
    INDEX
    Explanations

    large blocks of whitespace and the words "Act", "Code", "Ann", "example", "counsel", and "colloquy"

    oai_token-act-pair · gemini-2.0-flash

    legal texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     &___
    -0.94
     مرئيه
    -0.78
    AndEndTag
    -0.77
     OnInit
    -0.75
     محفوظة
    -0.69
    Билгалдахарш
    -0.69
     nahilalakip
    -0.68
    DataMember
    -0.68
     EconPapers
    -0.68
     مشين
    -0.66
    POSITIVE LOGITS
    <bos>
    1.23
     Deckel
    0.45
    ↵↵
    0.44
    ’
    0.43
     still
    0.41
    "]))
    0.41
     trot
    0.40
    '
    0.39
    Lesen
    0.39
    ').
    0.39
    Activations Density 1.391%

    No Known Activations