Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13553
    Prev
    Next
    INDEX
    Explanations

    descriptions of dresses, especially the style, neckline, and skirt type

    oai_token-act-pair · gemini-2.0-flash

    Fashion/dresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     HasFactory
    -0.84
    GraphicsUnit
    -0.67
    principalColumn
    -0.66
    UnknownFieldSet
    -0.62
     JAXBElement
    -0.62
     handleMessage
    -0.59
     betweenstory
    -0.59
    GeneratedMessage
    -0.58
     LUMP
    -0.58
    sidemargin
    -0.58
    POSITIVE LOGITS
     lingerie
    0.56
    nościo
    0.54
    <bos>
    0.54
     oprot
    0.48
     dentelle
    0.42
    doGet
    0.42
     Kleider
    0.41
     seksi
    0.41
    ladora
    0.41
    pagnes
    0.41
    Activations Density 0.459%

    No Known Activations