© 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. 9235
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and phrases related to fashion, technology or general appeal.

    oai_token-act-pair · gemini-2.0-flash

    expressions of appreciation or exclamation

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

    Positive experiences and excitement

    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
    XmlAccessorType
    -0.92
     jScrollPane
    -0.82
     GenerationType
    -0.82
     bezeichneter
    -0.81
     EconPapers
    -0.79
    ChildScrollView
    -0.75
    rrggbb
    -0.74
    ');?>
    -0.70
    GGI
    -0.69
     tartalomajánló
    -0.69
    POSITIVE LOGITS
    !
    0.58
     thanks
    0.53
    Thanks
    0.48
     Thanks
    0.47
     näin
    0.45
    .
    0.43
    בל
    0.43
     myö
    0.42
     meille
    0.42
     änd
    0.41
    Activations Density 3.929%

    No Known Activations