© 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. 14598
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to language, biology, geography, sewing and past events

    oai_token-act-pair · gemini-2.0-flash

    transmembrane

    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
    a
    -0.61
     reprendre
    -0.55
    xase
    -0.54
     trata
    -0.52
    liothèque
    -0.52
    منع
    -0.51
     cours
    -0.49
    uki
    -0.49
    acz
    -0.49
     Numerous
    -0.48
    POSITIVE LOGITS
    PreferredItem
    0.97
     Yom
    0.94
     Fama
    0.94
     Dm
    0.93
     Acme
    0.93
     DMC
    0.93
     NSM
    0.92
     CMM
    0.92
     APM
    0.92
     Nami
    0.91
    Activations Density 7.431%

    No Known Activations