© 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. 15897
    Prev
    Next
    INDEX
    Explanations

    Spanish words used in code examples, particularly related to variable assignment and decrementing within loops.

    oai_token-act-pair · gemini-2.0-flash

    lo

    np_max-act · gemini-2.0-flash

    Spanish text

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    MessageTagHelper
    -0.64
     CanadaChoose
    -0.61
    CodeAttribute
    -0.60
     يتيمه
    -0.58
    along
    -0.57
     Particularly
    -0.57
     OnTriggerEnter
    -0.56
    ConstraintMaker
    -0.56
    ticularly
    -0.56
    or
    -0.56
    POSITIVE LOGITS
    onViewCreated
    0.65
     ég
    0.60
    érêt
    0.60
    erapeu
    0.60
    Macros
    0.59
    LEncoder
    0.56
     quitt
    0.56
     phthal
    0.55
     henvisninger
    0.55
     quotidi
    0.55
    Activations Density 0.088%

    No Known Activations