© 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. 13156
    Prev
    Next
    INDEX
    Explanations

    spanish words related to programming languages

    oai_token-act-pair · gemini-2.0-flash

    Spanish

    np_max-act · gemini-2.0-flash

    Spanish words

    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
     auroit
    -1.02
     avoient
    -0.98
     feroit
    -0.98
     Efq
    -0.95
     pouvoit
    -0.93
     ainfi
    -0.93
     ARXIV
    -0.93
     Houſe
    -0.92
     anún
    -0.91
     crdi
    -0.90
    POSITIVE LOGITS
     a
    0.75
     an
    0.65
     E
    0.65
     es
    0.64
     As
    0.61
     For
    0.60
     It
    0.59
    án
    0.59
     To
    0.58
     con
    0.57
    Activations Density 0.431%

    No Known Activations