© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1625
    Prev
    Next
    INDEX
    Explanations

    the letter 'b' in parentheses or after underscores

    oai_token-act-pair · gemini-2.0-flash

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     b
    -1.98
    b
    -1.86
     B
    -1.09
    B
    -1.00
    getB
    -0.96
    bB
    -0.94
     getB
    -0.91
    bA
    -0.90
     б
    -0.88
     ب
    -0.84
    POSITIVE LOGITS
     GenerationType
    0.67
     Roskov
    0.66
    AutoresizingMask
    0.61
     ब्रेकडाउन
    0.59
    DataSetChanged
    0.59
    CloseOperation
    0.58
    ChildScrollView
    0.58
    abetes
    0.58
     مشين
    0.56
     linkovi
    0.56
    Activations Density 1.646%

    No Known Activations