© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5998
    Prev
    Next
    INDEX
    Explanations

    code, error, and profile related words in a mix of languages

    oai_token-act-pair · gemini-2.0-flash

    Portuguese

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     une
    -1.06
     una
    -1.03
    une
    -0.97
    Une
    -0.88
     Une
    -0.87
     eine
    -0.81
     μια
    -0.81
     uma
    -0.79
    Una
    -0.74
     Una
    -0.72
    POSITIVE LOGITS
     un
    0.77
     um
    0.76
     ein
    0.67
     Um
    0.65
    Um
    0.64
    Un
    0.62
     Ein
    0.61
    um
    0.59
    extAlignment
    0.57
    un
    0.57
    Activations Density 1.452%

    No Known Activations