© 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. 6082
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating the location or sequence of something

    oai_token-act-pair · gemini-2.0-flash

    Non-English, code

    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
    ⓧ
    -0.58
    ibatis
    -0.52
    Tikang
    -0.49
     Police
    -0.47
    Iron
    -0.46
    WebElementEntity
    -0.46
    Police
    -0.45
    ני
    -0.44
    IRON
    -0.44
    é
    -0.44
    POSITIVE LOGITS
    تقاوى
    0.80
     propOrder
    0.79
     autorytatywna
    0.73
     оригіналу
    0.69
    ſelf
    0.67
     */;
    0.67
     Мексичка
    0.66
    ContextHolder
    0.65
     GoogleFonts
    0.64
     myſelf
    0.64
    Activations Density 0.163%

    No Known Activations