© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10077
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    number 3

    np_max-act-logits · gemini-2.0-flash

    x

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Fifth
    -0.90
    Fifth
    -0.88
     fifth
    -0.82
    fifth
    -0.82
     FIFTH
    -0.66
    第五
    -0.64
     five
    -0.64
     Sixth
    -0.63
    seventh
    -0.63
     seventh
    -0.61
    POSITIVE LOGITS
    3
    1.74
     three
    1.11
    ３
    1.08
     ketiga
    1.00
     trois
    0.94
     ۳
    0.94
     tiga
    0.93
     Thirty
    0.89
     troisième
    0.88
     ३
    0.88
    Activations Density 8.067%

    No Known Activations