© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 1277
    Prev
    Next
    INDEX
    Explanations

    positive testimonials about a female person where the client is very happy with the service they received.

    oai_token-act-pair · gemini-2.0-flash

    Active experiences

    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
     nahilalakip
    -0.58
     Económica
    -0.47
    MemoryWarning
    -0.46
     Jusqu
    -0.42
    Pratique
    -0.42
    してくれます
    -0.42
    BoxShadow
    -0.41
     MainAxisSize
    -0.41
     ModelExpression
    -0.41
     Frenchmen
    -0.41
    POSITIVE LOGITS
    didSet
    0.60
    ropical
    0.59
    ỡng
    0.58
     gọn
    0.57
     BEAT
    0.56
    enido
    0.56
    beke
    0.56
     تضيفلها
    0.55
    endmodule
    0.55
    diman
    0.55
    Activations Density 4.324%

    No Known Activations