© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14523
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "col" followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    tokens related to 'col'

    np_token-act-pair-logits · gpt-4o-mini

    col

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    XmlAccessType
    -0.47
    eradish
    -0.43
     DBNull
    -0.42
    rip
    -0.41
     CURIAM
    -0.40
    ssch
    -0.38
     архивлан
    -0.36
     GetEnumerator
    -0.36
     biol
    -0.36
     bio
    -0.36
    POSITIVE LOGITS
    OGND
    0.79
    出版年
    0.75
    +#+#
    0.66
    ราะ
    0.65
     pleaſure
    0.62
     Савезне
    0.62
     nakalista
    0.60
    +#+
    0.60
     expérimentés
    0.60
     Paglinawan
    0.59
    Activations Density 0.302%

    No Known Activations