© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4084
    Prev
    Next
    INDEX
    Explanations

    words from the Croatian language having to do with using Facebook, especially those related to logging in or receiving codes

    oai_token-act-pair · gemini-2.0-flash

    pri

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     при
    -1.39
     przy
    -1.13
    При
    -1.10
    при
    -1.03
     При
    -0.98
     ПРИ
    -0.87
     při
    -0.85
    <bos>
    -0.84
     pri
    -0.82
    przy
    -0.82
    POSITIVE LOGITS
    cách
    0.64
    出版年
    0.63
    AxisAlignment
    0.59
    sphase
    0.57
     économ
    0.57
    Fonti
    0.56
    UserScript
    0.56
    醐
    0.55
    mals
    0.54
     colorless
    0.53
    Activations Density 2.047%

    No Known Activations