© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7737
    Prev
    Next
    INDEX
    Explanations

    the word 'building' as used in a technical context

    oai_token-act-pair · gemini-2.0-flash

    building

    np_max-act · gemini-2.0-flash
    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
    corazón
    -0.70
     his
    -0.64
     the
    -0.64
     this
    -0.64
     origines
    -0.59
     our
    -0.59
     my
    -0.57
    žad
    -0.57
     különböz
    -0.57
    alugar
    -0.56
    POSITIVE LOGITS
     StatelessWidget
    0.82
    yntaxException
    0.81
    )‏
    0.80
     }}">
    0.78
    yship
    0.77
     MotionEvent
    0.76
     StatefulWidget
    0.75
     endregion
    0.74
    endpush
    0.72
     gainera
    0.71
    Activations Density 1.190%

    No Known Activations