© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12555
    Prev
    Next
    INDEX
    Explanations

    words related to the senses, especially smell

    oai_token-act-pair · gemini-2.0-flash

    smells and scents

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

    Sounds and smells

    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
    MigrationBuilder
    -0.66
     kaarangay
    -0.61
    colns
    -0.48
     devriez
    -0.47
    aarrggbb
    -0.43
    ModelAttribute
    -0.43
     alın
    -0.43
    igail
    -0.43
    :+:
    -0.42
    σιμοποι
    -0.42
    POSITIVE LOGITS
     Administrativna
    0.64
     reverber
    0.63
    Literatur
    0.62
     Pingback
    0.61
     intptr
    0.59
    ">//
    0.58
    Hochspringen
    0.57
     waf
    0.57
     continuant
    0.57
    NUMX
    0.56
    Activations Density 3.188%

    No Known Activations