© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4737
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers

    oai_token-act-pair · gemini-2.0-flash

    nine

    np_max-act · gemini-2.0-flash
    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
     nine
    -2.16
     six
    -2.14
     seven
    -2.11
     eight
    -2.11
     five
    -2.11
     four
    -1.90
     twelve
    -1.90
     eleven
    -1.84
     ten
    -1.84
     thirteen
    -1.75
    POSITIVE LOGITS
    7
    1.08
    <bos>
    1.05
    5
    1.05
    9
    1.02
    6
    1.00
    4
    0.99
    8
    0.99
    3
    0.93
    0
    0.84
    ↵↵
    0.80
    Activations Density 1.090%

    No Known Activations