© 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. 7008
    Prev
    Next
    INDEX
    Explanations

    descriptions of women's fashion and accessories

    oai_token-act-pair · gemini-2.0-flash

    words related to fashion accessories, specifically shoes

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

    shoe heels

    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
    zeka
    -0.50
     petto
    -0.50
     oprot
    -0.50
     Mumford
    -0.50
    Apollo
    -0.49
    #+#
    -0.49
    }}$
    -0.49
    "]);
    -0.48
    }")
    -0.47
    "])
    -0.47
    POSITIVE LOGITS
     heels
    1.07
     Heels
    0.81
     heel
    0.70
    TestBed
    0.65
    MetaType
    0.61
     stiletto
    0.60
     esternos
    0.60
     sti
    0.59
    fillType
    0.59
     nakalista
    0.59
    Activations Density 0.755%

    No Known Activations