© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12830
    Prev
    Next
    INDEX
    Explanations

    acronyms, especially those of organizations or tools

    oai_token-act-pair · gemini-2.0-flash

    Acronyms

    np_max-act · gemini-2.0-flash

    acronyms

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    abestanden
    -0.86
    GEBURTSDATUM
    -0.68
    #+#
    -0.68
    তথ্যসূত্র
    -0.67
     مشين
    -0.66
    -0.64
     Majefty
    -0.64
     برانيه
    -0.62
     esternos
    -0.62
    IBarButtonItem
    -0.61
    POSITIVE LOGITS
     AppBundle
    0.42
     S
    0.41
     SSA
    0.40
     तह
    0.40
    replication
    0.40
    szt
    0.40
     gén
    0.40
     resultCode
    0.39
     Rtl
    0.39
    Merkmale
    0.38
    Activations Density 1.664%

    No Known Activations