© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13486
    Prev
    Next
    INDEX
    Explanations

    language related to fashion trends and shopping events

    oai_token-act-pair · gemini-2.0-flash

    Fashion, style, and beauty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    DeleteBehavior
    -0.50
    nextLine
    -0.48
    SuccessListener
    -0.46
     endommag
    -0.45
     GenerationType
    -0.43
    idste
    -0.41
    superuser
    -0.40
    }")]
    -0.40
    mtrl
    -0.40
     bescha
    -0.40
    POSITIVE LOGITS
    OGND
    0.69
    KURZBESCHREIBUNG
    0.67
    ütün
    0.65
    لينكات
    0.64
     >=",
    0.60
    SharedDtor
    0.58
     cherchés
    0.57
     للاسماء
    0.55
    StructEnd
    0.55
     समीक्षाओं
    0.55
    Activations Density 2.662%

    No Known Activations