© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13432
    Prev
    Next
    INDEX
    Explanations

    words in what appears to be Croatian related to email, verification, and inputting codes.

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    astify
    -0.94
     تضيفلها
    -0.89
    ISupport
    -0.85
    OGND
    -0.81
     ©️
    -0.75
    ьаж
    -0.72
    mentaux
    -0.69
     TabLayout
    -0.65
    ksikon
    -0.64
    навли
    -0.62
    POSITIVE LOGITS
    VELAND
    0.41
    anche
    0.40
    entry
    0.40
    根
    0.39
    mites
    0.39
     entry
    0.39
    theless
    0.39
    mopolitan
    0.38
    ankin
    0.38
    base
    0.38
    Activations Density 0.281%

    No Known Activations