© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14385
    Prev
    Next
    INDEX
    Explanations

    phrases like 'I am' and 'as' in the context of a technical discussion

    oai_token-act-pair · gemini-2.0-flash

    but

    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
     EconPapers
    -0.74
     he
    -0.71
     they
    -0.65
     she
    -0.63
     we
    -0.63
     it
    -0.56
     klubben
    -0.55
     egli
    -0.51
    __':
    -0.48
    ernalia
    -0.48
    POSITIVE LOGITS
     It
    0.95
     These
    0.90
     This
    0.83
     There
    0.82
     They
    0.78
     That
    0.78
     Our
    0.73
     Some
    0.73
     Each
    0.72
     Many
    0.72
    Activations Density 9.931%

    No Known Activations