© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 810
    Prev
    Next
    INDEX
    Explanations

    the letter K, especially when followed by other letters

    oai_token-act-pair · gemini-2.0-flash

    K

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     K
    -2.39
    K
    -2.06
     k
    -1.44
     К
    -1.26
    Ｋ
    -1.22
    k
    -1.11
    К
    -1.05
    Ks
    -0.87
    KK
    -0.81
     Ks
    -0.80
    POSITIVE LOGITS
    Rhestr
    0.80
     propOrder
    0.73
    clusal
    0.72
     faſt
    0.71
    IndentedString
    0.70
     iſt
    0.70
    setVerticalGroup
    0.69
    })*/
    0.69
    </tfoot>
    0.66
     purpoſe
    0.66
    Activations Density 0.640%

    No Known Activations