© 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. 11654
    Prev
    Next
    INDEX
    Explanations

    code, including numbers and x characters

    oai_token-act-pair · gemini-2.0-flash

    Code/Technical text

    np_max-act · gemini-2.0-flash

    say "2" Method used: 2 — because the following tokens are predominantly the numeral 2

    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
    1
    -1.81
    2
    -1.75
    3
    -1.67
    0
    -1.63
    4
    -1.61
    5
    -1.59
    9
    -1.48
    7
    -1.47
    6
    -1.47
    <bos>
    -1.47
    POSITIVE LOGITS
     Efq
    2.28
    ^(@)
    2.16
     myſelf
    2.03
    BibitemShut
    2.00
     Jefus
    1.98
     ſeveral
    1.91
     Monfieur
    1.89
     houſe
    1.88
     ſtate
    1.84
    ſelf
    1.84
    Activations Density 3.967%

    No Known Activations