© 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. 14616
    Prev
    Next
    INDEX
    Explanations

    the character sequence "chi"

    oai_token-act-pair · gemini-2.0-flash

    tokens related to "chi"

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

    chi

    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
    complexType
    -0.47
     post
    -0.46
    никах
    -0.45
    السكان
    -0.43
     industry
    -0.42
    tais
    -0.42
    oherty
    -0.42
    IVIA
    -0.41
     K
    -0.40
    ylvan
    -0.39
    POSITIVE LOGITS
    Архівовано
    0.68
     Roskov
    0.65
     chi̍t
    0.65
     AttributeSet
    0.65
     Consejos
    0.64
     kasarigan
    0.63
     MainAxisSize
    0.62
    ToScroll
    0.61
    ChildScrollView
    0.58
    AddTagHelper
    0.58
    Activations Density 0.269%

    No Known Activations