© 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. 13024
    Prev
    Next
    INDEX
    Explanations

    the word "means" in the context of describing a mechanical invention

    oai_token-act-pair · gemini-2.0-flash

    means

    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
     Efq
    -1.00
     uſ
    -0.97
     raiſ
    -0.95
     pleaſure
    -0.92
     purpoſe
    -0.90
     deſt
    -0.89
     juſt
    -0.88
     juſ
    -0.87
     whoſe
    -0.87
     myſelf
    -0.86
    POSITIVE LOGITS
    mybatisplus
    0.69
     चीज़ों
    0.63
    >{@
    0.59
    ynx
    0.58
    Rüyada
    0.58
    hoeddwyd
    0.57
    ...
    0.56
    awtextra
    0.55
     organise
    0.54
    providedIn
    0.54
    Activations Density 0.866%

    No Known Activations