© 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. 9880
    Prev
    Next
    INDEX
    Explanations

    the adjective "nice," sometimes with a preceding adverb

    oai_token-act-pair · gemini-2.0-flash

    nice

    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
     ་་
    -0.97
     Shakspeare
    -0.97
     Shaksp
    -0.95
     Pelop
    -0.94
     Neander
    -0.93
     PLWABN
    -0.93
     Walkover
    -0.93
     Elizabethan
    -0.92
     Houſe
    -0.91
     Anſ
    -0.91
    POSITIVE LOGITS
     
    0.71
     most
    0.69
     various
    0.64
    mense
    0.63
     many
    0.63
     first
    0.62
     long
    0.60
    ↵↵
    0.59
    es
    0.58
     the
    0.58
    Activations Density 1.778%

    No Known Activations