© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12444
    Prev
    Next
    INDEX
    Explanations

    technical computing terms, especially related to VPNs and software

    oai_token-act-pair · gemini-2.0-flash

    Computer systems and apps

    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
     sur
    -0.57
    ांत
    -0.50
     von
    -0.47
     Ka
    -0.47
    nik
    -0.47
    Point
    -0.46
    AutoScaleMode
    -0.45
     End
    -0.44
     تط
    -0.44
     Point
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.79
    oa̍t
    0.65
    )_/¯
    0.64
     Administrativna
    0.63
     Италијани
    0.60
    المكان
    0.59
    kuuta
    0.57
     Мексичка
    0.57
     typelib
    0.56
     صوتيه
    0.56
    Activations Density 1.498%

    No Known Activations