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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6241
    Prev
    Next
    INDEX
    Explanations

    business plans and ambiguous quantifiers

    oai_token-act-pair · gemini-2.0-flash

    plans

    np_max-act · gemini-2.0-flash

    plans

    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
     Jefus
    -0.73
     ſeveral
    -0.72
     Monfieur
    -0.70
     houſe
    -0.70
     Houſe
    -0.69
     Efq
    -0.67
     Majefty
    -0.66
     dafs
    -0.66
     Chriftian
    -0.65
     greateſt
    -0.65
    POSITIVE LOGITS
    <bos>
    0.60
     Nazionale
    0.58
    ECONDS
    0.56
    freiheit
    0.55
    AMPLES
    0.54
    اضر
    0.54
     really
    0.54
    ruvate
    0.54
    styrelsen
    0.53
    polator
    0.52
    Activations Density 1.446%

    No Known Activations