© 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. 2933
    Prev
    Next
    INDEX
    Explanations

    things related to ice cream and related treats

    oai_token-act-pair · gemini-2.0-flash

    terms related to ice cream

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

    ice

    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
    matchCondition
    -0.45
    格局
    -0.45
     consigo
    -0.45
    OPSIS
    -0.41
     hermanas
    -0.40
     sanitaires
    -0.40
     oreilles
    -0.40
    DoubleQuotes
    -0.40
    是以
    -0.40
     partenariat
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.76
     Савезне
    0.75
     nahilalakip
    0.71
     }{@
    0.66
     مرئيه
    0.66
     ostavi
    0.66
    ंदीखरीदारी
    0.65
     cream
    0.65
     Lightboxes
    0.63
     rink
    0.62
    Activations Density 0.670%

    No Known Activations